Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3488 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.6699. Min Act: -0.0000

Data Index: 78672 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.6580. Min Act: -0.0000

Data Index: 346638 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.6383. Min Act: -0.0000

Data Index: 719882 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.6100. Min Act: -0.0000

Data Index: 24778 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1318050 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5336. Min Act: -0.0000

Data Index: 607589 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5308. Min Act: 0.0000

Data Index: 1041847 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5475. Min Act: -0.0000

Data Index: 606835 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5129. Min Act: 0.0001

Data Index: 1035623 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1020121 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5320. Min Act: 0.0002

Data Index: 219521 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5219. Min Act: 0.0001

Data Index: 274 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1160359 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5114. Min Act: -0.0000

Data Index: 83300 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1021566 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5059. Min Act: -0.0000

Data Index: 452902 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1233565 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.5195. Min Act: -0.0000

Data Index: 989832 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4963. Min Act: -0.0000

Data Index: 853671 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.6699. Min Range: -0.6699

Max Act: 0.4916. Min Act: -0.0000

Data Index: 846622 (C4 (Web Text))

Max Activating Token Index: 39