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

Dataset: Open Web Text

Neuron 505 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: 2.0037. Min Range: -2.0037

Max Act: 1.9576. Min Act: -0.1700

Data Index: 3665797 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 2.0037. Min Range: -2.0037

Max Act: 2.0037. Min Act: -0.1699

Data Index: 7248765 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9806. Min Act: -0.1700

Data Index: 2962882 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9814. Min Act: -0.1699

Data Index: 1155294 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9776. Min Act: -0.1678

Data Index: 8695297 (Open Web Text)

Max Activating Token Index: 241

Text #5

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9761. Min Act: -0.1696

Data Index: 316631 (Open Web Text)

Max Activating Token Index: 935

Text #6

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9873. Min Act: -0.1700

Data Index: 4249367 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9575. Min Act: -0.1700

Data Index: 1684947 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9416. Min Act: -0.1699

Data Index: 3138588 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9601. Min Act: -0.1696

Data Index: 4084978 (Open Web Text)

Max Activating Token Index: 939

Text #10

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9440. Min Act: -0.1700

Data Index: 7124788 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9557. Min Act: -0.1699

Data Index: 6655186 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9367. Min Act: -0.1700

Data Index: 6485677 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9806. Min Act: -0.1696

Data Index: 2950654 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9400. Min Act: -0.1700

Data Index: 2640694 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9368. Min Act: -0.1674

Data Index: 5579565 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9430. Min Act: -0.1697

Data Index: 6069650 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9104. Min Act: -0.1700

Data Index: 7864915 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9313. Min Act: -0.1677

Data Index: 6834604 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 2.0037. Min Range: -2.0037

Max Act: 1.9431. Min Act: -0.1700

Data Index: 2445874 (Open Web Text)

Max Activating Token Index: 5