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

Dataset: Open Web Text

Neuron 1182 in Layer 2

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: 4.9359. Min Range: -4.9359

Max Act: 4.9359. Min Act: -0.1700

Data Index: 5180581 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.8974. Min Act: -0.1700

Data Index: 8614153 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.8213. Min Act: -0.1700

Data Index: 1063288 (Open Web Text)

Max Activating Token Index: 917

Text #3

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.8369. Min Act: -0.1679

Data Index: 3890080 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.8474. Min Act: -0.1700

Data Index: 5180579 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7771. Min Act: -0.1693

Data Index: 3887997 (Open Web Text)

Max Activating Token Index: 141

Text #6

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7833. Min Act: -0.1698

Data Index: 8181620 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7306. Min Act: -0.1696

Data Index: 4185172 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7224. Min Act: -0.1700

Data Index: 4579031 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7626. Min Act: -0.1663

Data Index: 7231771 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7544. Min Act: -0.1695

Data Index: 741641 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7487. Min Act: -0.1700

Data Index: 310993 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7753. Min Act: -0.1696

Data Index: 8318419 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.6867. Min Act: -0.1651

Data Index: 4940296 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7635. Min Act: -0.1699

Data Index: 6241999 (Open Web Text)

Max Activating Token Index: 739

Text #15

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7594. Min Act: -0.1695

Data Index: 2151869 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7022. Min Act: -0.1700

Data Index: 5731563 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7380. Min Act: -0.1700

Data Index: 2205488 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7340. Min Act: -0.1700

Data Index: 2376474 (Open Web Text)

Max Activating Token Index: 906

Text #19

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7447. Min Act: -0.1698

Data Index: 2677708 (Open Web Text)

Max Activating Token Index: 114