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

Dataset: Open Web Text

Neuron 1974 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: 3.7917. Min Range: -3.7917

Max Act: 3.7917. Min Act: -0.1700

Data Index: 3901544 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.7577. Min Act: -0.1700

Data Index: 4700255 (Open Web Text)

Max Activating Token Index: 838

Text #2

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.7049. Min Act: -0.1700

Data Index: 434287 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.7064. Min Act: -0.1700

Data Index: 2559647 (Open Web Text)

Max Activating Token Index: 503

Text #4

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6589. Min Act: -0.1700

Data Index: 4216751 (Open Web Text)

Max Activating Token Index: 526

Text #5

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6596. Min Act: -0.1700

Data Index: 5445823 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6475. Min Act: -0.1700

Data Index: 1857159 (Open Web Text)

Max Activating Token Index: 445

Text #7

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6807. Min Act: -0.1700

Data Index: 349918 (Open Web Text)

Max Activating Token Index: 842

Text #8

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6308. Min Act: -0.1700

Data Index: 2715476 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1606057 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6386. Min Act: -0.1700

Data Index: 5285113 (Open Web Text)

Max Activating Token Index: 505

Text #11

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6462. Min Act: -0.1700

Data Index: 2085951 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6121. Min Act: -0.1700

Data Index: 1688920 (Open Web Text)

Max Activating Token Index: 296

Text #13

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6052. Min Act: -0.1700

Data Index: 2564514 (Open Web Text)

Max Activating Token Index: 931

Text #14

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6213. Min Act: -0.1700

Data Index: 6618992 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.5941. Min Act: -0.1700

Data Index: 6566603 (Open Web Text)

Max Activating Token Index: 274

Text #16

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.6049. Min Act: -0.1700

Data Index: 866254 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.5993. Min Act: -0.1700

Data Index: 1992317 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.5713. Min Act: -0.1700

Data Index: 4657720 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.5834. Min Act: -0.1700

Data Index: 112315 (Open Web Text)

Max Activating Token Index: 416