< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 972 in Layer 2

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: 2.8459. Min Range: -2.8459

Max Act: 2.8459. Min Act: -0.1700

Data Index: 1454580 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7865. Min Act: -0.1700

Data Index: 4226460 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7742. Min Act: -0.1700

Data Index: 319403 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7865. Min Act: -0.1700

Data Index: 5384324 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7742. Min Act: -0.1700

Data Index: 7374445 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7554. Min Act: -0.1700

Data Index: 4623347 (Open Web Text)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7890. Min Act: -0.1700

Data Index: 5097637 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.8000. Min Act: -0.1700

Data Index: 6928752 (Open Web Text)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7583. Min Act: -0.1700

Data Index: 1424367 (Open Web Text)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7761. Min Act: -0.1700

Data Index: 6072472 (Open Web Text)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7637. Min Act: -0.1700

Data Index: 3418261 (Open Web Text)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7638. Min Act: -0.1700

Data Index: 5498013 (Open Web Text)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7440. Min Act: -0.1700

Data Index: 8270055 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7342. Min Act: -0.1700

Data Index: 4630086 (Open Web Text)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7323. Min Act: -0.1700

Data Index: 694082 (Open Web Text)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7084. Min Act: -0.1700

Data Index: 1837706 (Open Web Text)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7456. Min Act: -0.1700

Data Index: 7201046 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7359. Min Act: -0.1700

Data Index: 6355875 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7295. Min Act: -0.1700

Data Index: 2518814 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8459. Min Range: -2.8459

Max Act: 2.7456. Min Act: -0.1700

Data Index: 5572591 (Open Web Text)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #19