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

Dataset: Open Web Text

Neuron 951 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: 3.7895. Min Range: -3.7895

Max Act: 3.7895. Min Act: -0.1700

Data Index: 8526860 (Open Web Text)

Max Activating Token Index: 422

Text #1

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6978. Min Act: -0.1700

Data Index: 1899042 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6846. Min Act: -0.1700

Data Index: 1989057 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6943. Min Act: -0.1700

Data Index: 7994294 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6496. Min Act: -0.1700

Data Index: 6644755 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6689. Min Act: -0.1700

Data Index: 3090350 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6278. Min Act: -0.1700

Data Index: 1143728 (Open Web Text)

Max Activating Token Index: 632

Text #7

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6348. Min Act: -0.1700

Data Index: 6474814 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6514. Min Act: -0.1700

Data Index: 6922529 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5994. Min Act: -0.1700

Data Index: 1335145 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6469. Min Act: -0.1700

Data Index: 8512093 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6031. Min Act: -0.1700

Data Index: 3051760 (Open Web Text)

Max Activating Token Index: 586

Text #12

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5929. Min Act: -0.1700

Data Index: 8294852 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6096. Min Act: -0.1700

Data Index: 6031488 (Open Web Text)

Max Activating Token Index: 475

Text #14

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5742. Min Act: -0.1700

Data Index: 3157627 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6174. Min Act: -0.1700

Data Index: 6346006 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5953. Min Act: -0.1700

Data Index: 5195215 (Open Web Text)

Max Activating Token Index: 278

Text #17

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.6184. Min Act: -0.1700

Data Index: 4831974 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5816. Min Act: -0.1700

Data Index: 4367848 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 3.7895. Min Range: -3.7895

Max Act: 3.5906. Min Act: -0.1700

Data Index: 6946958 (Open Web Text)

Max Activating Token Index: 588