< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2793 in Layer 4

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: 2.9220. Min Range: -2.9220

Max Act: 2.9220. Min Act: -0.1700

Data Index: 1393147 (Open Web Text)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.8655. Min Act: -0.1700

Data Index: 4539674 (Open Web Text)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.8533. Min Act: -0.1700

Data Index: 7021500 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7952. Min Act: -0.1700

Data Index: 1649349 (Open Web Text)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7815. Min Act: -0.1700

Data Index: 3343848 (Open Web Text)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7256. Min Act: -0.1700

Data Index: 697127 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7197. Min Act: -0.1700

Data Index: 6063324 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7188. Min Act: -0.1700

Data Index: 2253932 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6905. Min Act: -0.1700

Data Index: 3736492 (Open Web Text)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7113. Min Act: -0.1700

Data Index: 1144810 (Open Web Text)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6987. Min Act: -0.1700

Data Index: 4669207 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.7046. Min Act: -0.1700

Data Index: 990362 (Open Web Text)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6740. Min Act: -0.1700

Data Index: 836079 (Open Web Text)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6789. Min Act: -0.1700

Data Index: 8002171 (Open Web Text)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6620. Min Act: -0.1700

Data Index: 752948 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6515. Min Act: -0.1700

Data Index: 7031600 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6686. Min Act: -0.1700

Data Index: 3498637 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6577. Min Act: -0.1700

Data Index: 2245561 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6690. Min Act: -0.1700

Data Index: 5813062 (Open Web Text)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9220. Min Range: -2.9220

Max Act: 2.6581. Min Act: -0.1700

Data Index: 543582 (Open Web Text)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #19