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

Dataset: Open Web Text

Neuron 626 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: 5.3247. Min Range: -5.3247

Max Act: 5.3247. Min Act: -0.1700

Data Index: 4641314 (Open Web Text)

Max Activating Token Index: 566

Text #1

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2745. Min Act: -0.1700

Data Index: 7964020 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2647. Min Act: -0.1700

Data Index: 2925168 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2178. Min Act: -0.1700

Data Index: 4785521 (Open Web Text)

Max Activating Token Index: 59

Text #4

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2493. Min Act: -0.1700

Data Index: 3439979 (Open Web Text)

Max Activating Token Index: 810

Text #5

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2401. Min Act: -0.1700

Data Index: 4421798 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2045. Min Act: -0.1700

Data Index: 5776569 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.2274. Min Act: -0.1700

Data Index: 2593552 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1617. Min Act: -0.1700

Data Index: 5062507 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1821. Min Act: -0.1700

Data Index: 12220 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1828. Min Act: -0.1700

Data Index: 3995662 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1778. Min Act: -0.1700

Data Index: 3512609 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1746. Min Act: -0.1700

Data Index: 524981 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1461. Min Act: -0.1700

Data Index: 8446356 (Open Web Text)

Max Activating Token Index: 283

Text #14

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1318. Min Act: -0.1700

Data Index: 5101295 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1530. Min Act: -0.1700

Data Index: 2560494 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1449. Min Act: -0.1700

Data Index: 2210979 (Open Web Text)

Max Activating Token Index: 591

Text #17

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1522. Min Act: -0.1700

Data Index: 5188894 (Open Web Text)

Max Activating Token Index: 669

Text #18

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1199. Min Act: -0.1700

Data Index: 5578995 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1477. Min Act: -0.1700

Data Index: 3155052 (Open Web Text)

Max Activating Token Index: 576