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

Dataset: Open Web Text

Neuron 2590 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: 3.4317. Min Range: -3.4317

Max Act: 3.4317. Min Act: -0.1700

Data Index: 376697 (Open Web Text)

Max Activating Token Index: 166

Text #1

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3858. Min Act: -0.1700

Data Index: 2553653 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3814. Min Act: -0.1700

Data Index: 3856246 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3714. Min Act: -0.1700

Data Index: 6836391 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3669. Min Act: -0.1700

Data Index: 3351652 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3832. Min Act: -0.1700

Data Index: 8555492 (Open Web Text)

Max Activating Token Index: 625

Text #6

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3495. Min Act: -0.1700

Data Index: 6845889 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3514. Min Act: -0.1700

Data Index: 3345330 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3564. Min Act: -0.1700

Data Index: 5842351 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3385. Min Act: -0.1700

Data Index: 710034 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3604. Min Act: -0.1700

Data Index: 6044404 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3415. Min Act: -0.1700

Data Index: 7824555 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3454. Min Act: -0.1700

Data Index: 3521345 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3510. Min Act: -0.1700

Data Index: 5168871 (Open Web Text)

Max Activating Token Index: 169

Text #14

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3406. Min Act: -0.1700

Data Index: 2030748 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3243. Min Act: -0.1700

Data Index: 5411940 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3176. Min Act: -0.1700

Data Index: 6329950 (Open Web Text)

Max Activating Token Index: 122

Text #17

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3279. Min Act: -0.1700

Data Index: 7111038 (Open Web Text)

Max Activating Token Index: 822

Text #18

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3222. Min Act: -0.1700

Data Index: 2020894 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3060. Min Act: -0.1700

Data Index: 5141654 (Open Web Text)

Max Activating Token Index: 766