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

Dataset: Open Web Text

Neuron 2990 in Layer 4

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: 2.0977. Min Range: -2.0977

Max Act: 2.0977. Min Act: -0.1700

Data Index: 5751368 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0946. Min Act: -0.1700

Data Index: 6404560 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0537. Min Act: -0.1700

Data Index: 4780182 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0617. Min Act: -0.1700

Data Index: 3133971 (Open Web Text)

Max Activating Token Index: 584

Text #4

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0435. Min Act: -0.1700

Data Index: 6261846 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0362. Min Act: -0.1700

Data Index: 8371183 (Open Web Text)

Max Activating Token Index: 883

Text #6

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0611. Min Act: -0.1700

Data Index: 1092996 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0594. Min Act: -0.1700

Data Index: 539944 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0310. Min Act: -0.1700

Data Index: 6750965 (Open Web Text)

Max Activating Token Index: 979

Text #9

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0337. Min Act: -0.1700

Data Index: 3334616 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0467. Min Act: -0.1700

Data Index: 978846 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0356. Min Act: -0.1700

Data Index: 3562115 (Open Web Text)

Max Activating Token Index: 364

Text #12

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0445. Min Act: -0.1700

Data Index: 7064963 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0452. Min Act: -0.1700

Data Index: 1555694 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0397. Min Act: -0.1700

Data Index: 5392658 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0189. Min Act: -0.1700

Data Index: 6228553 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0315. Min Act: -0.1700

Data Index: 1241064 (Open Web Text)

Max Activating Token Index: 768

Text #17

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0185. Min Act: -0.1700

Data Index: 1028042 (Open Web Text)

Max Activating Token Index: 131

Text #18

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0058. Min Act: -0.1700

Data Index: 7067855 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 2.0977. Min Range: -2.0977

Max Act: 2.0007. Min Act: -0.1700

Data Index: 6556673 (Open Web Text)

Max Activating Token Index: 871