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

Dataset: Open Web Text

Neuron 2531 in Layer 1

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: 4.7634. Min Range: -4.7634

Max Act: 4.7634. Min Act: -0.1700

Data Index: 7392987 (Open Web Text)

Max Activating Token Index: 61

Text #1

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.7170. Min Act: -0.1700

Data Index: 8332207 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.7327. Min Act: -0.1700

Data Index: 4725276 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6722. Min Act: -0.1700

Data Index: 1639954 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6983. Min Act: -0.1700

Data Index: 5807940 (Open Web Text)

Max Activating Token Index: 112

Text #5

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6804. Min Act: -0.1700

Data Index: 3398784 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.7099. Min Act: -0.1700

Data Index: 3990510 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6614. Min Act: -0.1700

Data Index: 8288437 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6804. Min Act: -0.1700

Data Index: 7064711 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6430. Min Act: -0.1700

Data Index: 2993228 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6526. Min Act: -0.1700

Data Index: 4796914 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6431. Min Act: -0.1700

Data Index: 4521113 (Open Web Text)

Max Activating Token Index: 907

Text #12

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6733. Min Act: -0.1700

Data Index: 8813974 (Open Web Text)

Max Activating Token Index: 161

Text #13

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6463. Min Act: -0.1700

Data Index: 5309757 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6262. Min Act: -0.1700

Data Index: 7145354 (Open Web Text)

Max Activating Token Index: 971

Text #15

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6311. Min Act: -0.1700

Data Index: 3381392 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6128. Min Act: -0.1700

Data Index: 6937508 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6430. Min Act: -0.1700

Data Index: 6687334 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6229. Min Act: -0.1700

Data Index: 5691525 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 4.7634. Min Range: -4.7634

Max Act: 4.6322. Min Act: -0.1700

Data Index: 4871407 (Open Web Text)

Max Activating Token Index: 303