< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1936 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.7667. Min Act: -0.1700

Data Index: 7393695 (Open Web Text)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6511. Min Act: -0.1700

Data Index: 8480544 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6434. Min Act: -0.1700

Data Index: 8736657 (Open Web Text)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6342. Min Act: -0.1700

Data Index: 5161857 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6344. Min Act: -0.1700

Data Index: 4483540 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6442. Min Act: -0.1700

Data Index: 2579140 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6288. Min Act: -0.1700

Data Index: 6383134 (Open Web Text)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6205. Min Act: -0.1700

Data Index: 1748020 (Open Web Text)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6089. Min Act: -0.1700

Data Index: 4370876 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5880. Min Act: -0.1700

Data Index: 8191527 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6096. Min Act: -0.1700

Data Index: 5507857 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6052. Min Act: -0.1700

Data Index: 4187156 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6069. Min Act: -0.1700

Data Index: 8399313 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.6443. Min Act: -0.1700

Data Index: 6160151 (Open Web Text)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5859. Min Act: -0.1700

Data Index: 1149947 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5852. Min Act: -0.1700

Data Index: 6950942 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5797. Min Act: -0.1700

Data Index: 713414 (Open Web Text)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5840. Min Act: -0.1700

Data Index: 8338430 (Open Web Text)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5959. Min Act: -0.1700

Data Index: 3790551 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7667. Min Range: -2.7667

Max Act: 2.5819. Min Act: -0.1700

Data Index: 6975267 (Open Web Text)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #19