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

Dataset: Open Web Text

Neuron 826 in Layer 0

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: 11.6382. Min Range: -11.6382

Max Act: 11.6382. Min Act: -0.1700

Data Index: 350652 (Open Web Text)

Max Activating Token Index: 444

Text #1

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.3685. Min Act: -0.1700

Data Index: 98036 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.3083. Min Act: -0.1700

Data Index: 2487690 (Open Web Text)

Max Activating Token Index: 969

Text #3

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.2167. Min Act: -0.1700

Data Index: 1325262 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.1439. Min Act: -0.1700

Data Index: 7218903 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.0887. Min Act: -0.1700

Data Index: 5480222 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.0329. Min Act: -0.1700

Data Index: 449882 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.0505. Min Act: -0.1700

Data Index: 2715750 (Open Web Text)

Max Activating Token Index: 989

Text #8

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.9339. Min Act: -0.1700

Data Index: 3015226 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.9291. Min Act: -0.1700

Data Index: 8532366 (Open Web Text)

Max Activating Token Index: 988

Text #10

Max Range: 11.6382. Min Range: -11.6382

Max Act: 11.0029. Min Act: -0.1700

Data Index: 2699829 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.9194. Min Act: -0.1700

Data Index: 8429356 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.8003. Min Act: -0.1700

Data Index: 2043876 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.7156. Min Act: -0.1700

Data Index: 3340070 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.7315. Min Act: -0.1700

Data Index: 4730302 (Open Web Text)

Max Activating Token Index: 958

Text #15

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.8424. Min Act: -0.1700

Data Index: 2612639 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.7714. Min Act: -0.1700

Data Index: 2526773 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.6826. Min Act: -0.1700

Data Index: 8342613 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.5546. Min Act: -0.1700

Data Index: 7101969 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 11.6382. Min Range: -11.6382

Max Act: 10.5938. Min Act: -0.1700

Data Index: 8101409 (Open Web Text)

Max Activating Token Index: 1023