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

Dataset: Open Web Text

Neuron 2283 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: 3.2655. Min Range: -3.2655

Max Act: 3.2655. Min Act: -0.1700

Data Index: 1365872 (Open Web Text)

Max Activating Token Index: 770

Text #1

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1790. Min Act: -0.1700

Data Index: 8294208 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1831. Min Act: -0.1700

Data Index: 6587541 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1512. Min Act: -0.1700

Data Index: 1261724 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1203. Min Act: -0.1700

Data Index: 1601749 (Open Web Text)

Max Activating Token Index: 865

Text #5

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1603. Min Act: -0.1700

Data Index: 6444610 (Open Web Text)

Max Activating Token Index: 816

Text #6

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1193. Min Act: -0.1700

Data Index: 8801038 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.1227. Min Act: -0.1700

Data Index: 6364199 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0967. Min Act: -0.1700

Data Index: 877250 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0939. Min Act: -0.1700

Data Index: 1380323 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0813. Min Act: -0.1700

Data Index: 6010924 (Open Web Text)

Max Activating Token Index: 227

Text #11

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0920. Min Act: -0.1700

Data Index: 4910886 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0813. Min Act: -0.1700

Data Index: 3043955 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0824. Min Act: -0.1700

Data Index: 3447982 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0547. Min Act: -0.1700

Data Index: 7361678 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0689. Min Act: -0.1700

Data Index: 5718671 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0850. Min Act: -0.1700

Data Index: 5079838 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0582. Min Act: -0.1700

Data Index: 5551439 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0454. Min Act: -0.1700

Data Index: 7386683 (Open Web Text)

Max Activating Token Index: 629

Text #19

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.0295. Min Act: -0.1700

Data Index: 1612980 (Open Web Text)

Max Activating Token Index: 782