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

Dataset: Open Web Text

Neuron 956 in Layer 6

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: 4.1286. Min Range: -4.1286

Max Act: 4.1286. Min Act: -0.1698

Data Index: 4603848 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9129. Min Act: -0.1557

Data Index: 8243528 (Open Web Text)

Max Activating Token Index: 896

Text #2

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8982. Min Act: -0.1696

Data Index: 6101883 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9384. Min Act: -0.1683

Data Index: 7529868 (Open Web Text)

Max Activating Token Index: 471

Text #4

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9869. Min Act: -0.1696

Data Index: 7154894 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9367. Min Act: -0.1671

Data Index: 3132832 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9014. Min Act: -0.1700

Data Index: 2867788 (Open Web Text)

Max Activating Token Index: 255

Text #7

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8978. Min Act: -0.1699

Data Index: 4987379 (Open Web Text)

Max Activating Token Index: 637

Text #8

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8639. Min Act: -0.1627

Data Index: 8470747 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8297. Min Act: -0.1695

Data Index: 2505929 (Open Web Text)

Max Activating Token Index: 375

Text #10

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8189. Min Act: -0.1700

Data Index: 8147326 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8131. Min Act: -0.1696

Data Index: 728854 (Open Web Text)

Max Activating Token Index: 718

Text #12

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8454. Min Act: -0.1547

Data Index: 6534958 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7856. Min Act: -0.1700

Data Index: 1810854 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7934. Min Act: -0.1676

Data Index: 4749317 (Open Web Text)

Max Activating Token Index: 716

Text #15

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8390. Min Act: -0.1700

Data Index: 6125016 (Open Web Text)

Max Activating Token Index: 786

Text #16

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8103. Min Act: -0.1700

Data Index: 7839195 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7403. Min Act: -0.1695

Data Index: 6286287 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7928. Min Act: -0.1700

Data Index: 4839509 (Open Web Text)

Max Activating Token Index: 672

Text #19

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.7946. Min Act: -0.1671

Data Index: 3535993 (Open Web Text)

Max Activating Token Index: 249