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

Dataset: Open Web Text

Neuron 74 in Layer 5

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: 4.5382. Min Range: -4.5382

Max Act: 4.5363. Min Act: -0.1700

Data Index: 7621587 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.5382. Min Act: -0.1700

Data Index: 6231796 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.5105. Min Act: -0.1700

Data Index: 8095788 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.5162. Min Act: -0.1700

Data Index: 8095780 (Open Web Text)

Max Activating Token Index: 516

Text #4

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4534. Min Act: -0.1700

Data Index: 4221621 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4383. Min Act: -0.1700

Data Index: 5842621 (Open Web Text)

Max Activating Token Index: 567

Text #6

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4502. Min Act: -0.1700

Data Index: 1144281 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4512. Min Act: -0.1700

Data Index: 6231797 (Open Web Text)

Max Activating Token Index: 353

Text #8

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3916. Min Act: -0.1700

Data Index: 3470821 (Open Web Text)

Max Activating Token Index: 524

Text #9

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4171. Min Act: -0.1700

Data Index: 8095787 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4311. Min Act: -0.1700

Data Index: 6231794 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4166. Min Act: -0.1700

Data Index: 842020 (Open Web Text)

Max Activating Token Index: 653

Text #12

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4231. Min Act: -0.1700

Data Index: 8794129 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3981. Min Act: -0.1700

Data Index: 3470822 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3735. Min Act: -0.1700

Data Index: 3119747 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3833. Min Act: -0.1700

Data Index: 1144274 (Open Web Text)

Max Activating Token Index: 864

Text #16

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3982. Min Act: -0.1700

Data Index: 4221622 (Open Web Text)

Max Activating Token Index: 838

Text #17

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.4039. Min Act: -0.1700

Data Index: 8095785 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3279. Min Act: -0.1700

Data Index: 7808342 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 4.5382. Min Range: -4.5382

Max Act: 4.3828. Min Act: -0.1700

Data Index: 4158530 (Open Web Text)

Max Activating Token Index: 748