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

Dataset: Open Web Text

Neuron 1986 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: 5.1345. Min Range: -5.1345

Max Act: 5.1345. Min Act: -0.1700

Data Index: 6653954 (Open Web Text)

Max Activating Token Index: 333

Text #1

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0937. Min Act: -0.1700

Data Index: 5379148 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0734. Min Act: -0.1700

Data Index: 2793991 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0576. Min Act: -0.1700

Data Index: 84719 (Open Web Text)

Max Activating Token Index: 444

Text #4

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0630. Min Act: -0.1700

Data Index: 2826962 (Open Web Text)

Max Activating Token Index: 681

Text #5

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0695. Min Act: -0.1700

Data Index: 8353018 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0886. Min Act: -0.1700

Data Index: 8282276 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0780. Min Act: -0.1700

Data Index: 2050510 (Open Web Text)

Max Activating Token Index: 159

Text #8

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0421. Min Act: -0.1700

Data Index: 6980090 (Open Web Text)

Max Activating Token Index: 744

Text #9

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0214. Min Act: -0.1700

Data Index: 5085142 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0437. Min Act: -0.1700

Data Index: 4420396 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0290. Min Act: -0.1700

Data Index: 8173987 (Open Web Text)

Max Activating Token Index: 670

Text #12

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0279. Min Act: -0.1700

Data Index: 8154759 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0319. Min Act: -0.1700

Data Index: 3905803 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0176. Min Act: -0.1700

Data Index: 6109117 (Open Web Text)

Max Activating Token Index: 514

Text #15

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0371. Min Act: -0.1700

Data Index: 6081002 (Open Web Text)

Max Activating Token Index: 568

Text #16

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0475. Min Act: -0.1700

Data Index: 5552611 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0334. Min Act: -0.1700

Data Index: 5260035 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0180. Min Act: -0.1700

Data Index: 5184041 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 5.1345. Min Range: -5.1345

Max Act: 5.0208. Min Act: -0.1700

Data Index: 1158213 (Open Web Text)

Max Activating Token Index: 92