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

Dataset: Open Web Text

Neuron 1674 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: 5.9521. Min Range: -5.9521

Max Act: 5.9521. Min Act: -0.1700

Data Index: 5029164 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.6295. Min Act: -0.1700

Data Index: 6640493 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.5976. Min Act: -0.1700

Data Index: 7222976 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.4891. Min Act: -0.1700

Data Index: 7659337 (Open Web Text)

Max Activating Token Index: 985

Text #4

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.5228. Min Act: -0.1700

Data Index: 2792677 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.4941. Min Act: -0.1700

Data Index: 6593696 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.5005. Min Act: -0.1700

Data Index: 3201465 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.4776. Min Act: -0.1700

Data Index: 6454764 (Open Web Text)

Max Activating Token Index: 868

Text #8

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.4077. Min Act: -0.1700

Data Index: 4193887 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.4024. Min Act: -0.1700

Data Index: 4038948 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.4028. Min Act: -0.1700

Data Index: 6804992 (Open Web Text)

Max Activating Token Index: 756

Text #11

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.3774. Min Act: -0.1700

Data Index: 2957341 (Open Web Text)

Max Activating Token Index: 939

Text #12

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.3723. Min Act: -0.1700

Data Index: 2851203 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.3578. Min Act: -0.1700

Data Index: 2889294 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.3355. Min Act: -0.1700

Data Index: 6410328 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.3096. Min Act: -0.1700

Data Index: 8434966 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.2956. Min Act: -0.1700

Data Index: 3229787 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.2784. Min Act: -0.1700

Data Index: 2003219 (Open Web Text)

Max Activating Token Index: 330

Text #18

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.2338. Min Act: -0.1700

Data Index: 5999551 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 5.9521. Min Range: -5.9521

Max Act: 5.2017. Min Act: -0.1700

Data Index: 1651213 (Open Web Text)

Max Activating Token Index: 375