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

Dataset: Open Web Text

Neuron 767 in Layer 5

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: 6.1270. Min Range: -6.1270

Max Act: 6.1270. Min Act: -0.1700

Data Index: 4547340 (Open Web Text)

Max Activating Token Index: 891

Text #1

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.7417. Min Act: -0.1700

Data Index: 8397939 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.7053. Min Act: -0.1700

Data Index: 4355777 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.7168. Min Act: -0.1700

Data Index: 7906438 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.7138. Min Act: -0.1700

Data Index: 8671819 (Open Web Text)

Max Activating Token Index: 604

Text #5

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.7023. Min Act: -0.1700

Data Index: 311363 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.6758. Min Act: -0.1700

Data Index: 1171596 (Open Web Text)

Max Activating Token Index: 604

Text #7

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.5586. Min Act: -0.1700

Data Index: 513294 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.6104. Min Act: -0.1700

Data Index: 6437158 (Open Web Text)

Max Activating Token Index: 999

Text #9

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.5417. Min Act: -0.1699

Data Index: 7645093 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.5523. Min Act: -0.1700

Data Index: 8127567 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.5159. Min Act: -0.1700

Data Index: 6343521 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4625. Min Act: -0.1700

Data Index: 6352520 (Open Web Text)

Max Activating Token Index: 969

Text #13

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4561. Min Act: -0.1700

Data Index: 7184329 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4323. Min Act: -0.1700

Data Index: 438005 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4208. Min Act: -0.1696

Data Index: 3041368 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4406. Min Act: -0.1700

Data Index: 2091941 (Open Web Text)

Max Activating Token Index: 919

Text #17

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4179. Min Act: -0.1700

Data Index: 4547339 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4482. Min Act: -0.1700

Data Index: 4820690 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 6.1270. Min Range: -6.1270

Max Act: 5.4318. Min Act: -0.1700

Data Index: 5517608 (Open Web Text)

Max Activating Token Index: 421