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

Dataset: Open Web Text

Neuron 1149 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: 6.5326. Min Range: -6.5326

Max Act: 6.5218. Min Act: -0.1700

Data Index: 5106526 (Open Web Text)

Max Activating Token Index: 627

Text #1

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.5326. Min Act: -0.1700

Data Index: 4493286 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.3994. Min Act: -0.1700

Data Index: 7324978 (Open Web Text)

Max Activating Token Index: 121

Text #3

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1515. Min Act: -0.1700

Data Index: 5973493 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.2635. Min Act: -0.1700

Data Index: 7040046 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1755. Min Act: -0.1700

Data Index: 5466003 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1381. Min Act: -0.1700

Data Index: 503533 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1533. Min Act: -0.1700

Data Index: 7679238 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1497. Min Act: -0.1700

Data Index: 3252323 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1154. Min Act: -0.1700

Data Index: 312952 (Open Web Text)

Max Activating Token Index: 708

Text #10

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1154. Min Act: -0.1700

Data Index: 6948810 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.1149. Min Act: -0.1700

Data Index: 5420603 (Open Web Text)

Max Activating Token Index: 929

Text #12

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.0899. Min Act: -0.1700

Data Index: 315382 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.0378. Min Act: -0.1700

Data Index: 4059560 (Open Web Text)

Max Activating Token Index: 997

Text #14

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.0647. Min Act: -0.1700

Data Index: 418233 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 6.5326. Min Range: -6.5326

Max Act: 5.9457. Min Act: -0.1700

Data Index: 6167980 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 6.5326. Min Range: -6.5326

Max Act: 5.9466. Min Act: -0.1700

Data Index: 747185 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.0226. Min Act: -0.1700

Data Index: 2914938 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 6.5326. Min Range: -6.5326

Max Act: 5.9743. Min Act: -0.1700

Data Index: 3667386 (Open Web Text)

Max Activating Token Index: 325

Text #19

Max Range: 6.5326. Min Range: -6.5326

Max Act: 6.0155. Min Act: -0.1700

Data Index: 8810006 (Open Web Text)

Max Activating Token Index: 175