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

Dataset: Open Web Text

Neuron 937 in Layer 4

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: 4.1205. Min Range: -4.1205

Max Act: 4.1205. Min Act: -0.1700

Data Index: 6641465 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.9527. Min Act: -0.1700

Data Index: 8602382 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.9131. Min Act: -0.1700

Data Index: 4559488 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8962. Min Act: -0.1700

Data Index: 3107897 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.9124. Min Act: -0.1700

Data Index: 6319370 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.9008. Min Act: -0.1700

Data Index: 6336047 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8845. Min Act: -0.1700

Data Index: 7979107 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.9053. Min Act: -0.1700

Data Index: 2321797 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8898. Min Act: -0.1700

Data Index: 1114273 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.9033. Min Act: -0.1700

Data Index: 3736966 (Open Web Text)

Max Activating Token Index: 185

Text #10

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8674. Min Act: -0.1700

Data Index: 1630020 (Open Web Text)

Max Activating Token Index: 954

Text #11

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8548. Min Act: -0.1700

Data Index: 311582 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8602. Min Act: -0.1700

Data Index: 7469483 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8714. Min Act: -0.1700

Data Index: 4452516 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8515. Min Act: -0.1700

Data Index: 4071230 (Open Web Text)

Max Activating Token Index: 667

Text #15

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8543. Min Act: -0.1700

Data Index: 935615 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8807. Min Act: -0.1700

Data Index: 3891623 (Open Web Text)

Max Activating Token Index: 884

Text #17

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8402. Min Act: -0.1700

Data Index: 2412274 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8495. Min Act: -0.1700

Data Index: 4829755 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.8606. Min Act: -0.1700

Data Index: 4655746 (Open Web Text)

Max Activating Token Index: 39