Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.6222. Min Act: -0.0000

Data Index: 805625 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5719. Min Act: -0.0000

Data Index: 148452 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5305. Min Act: -0.0000

Data Index: 318830 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5283. Min Act: -0.0000

Data Index: 801143 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1276642 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4712. Min Act: -0.0000

Data Index: 562863 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4281. Min Act: -0.0000

Data Index: 517295 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4568. Min Act: -0.0000

Data Index: 14507 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4535. Min Act: -0.0000

Data Index: 885016 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1082654 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4612. Min Act: -0.0000

Data Index: 327309 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4408. Min Act: -0.0000

Data Index: 304207 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4200. Min Act: -0.0000

Data Index: 340412 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1010157 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4154. Min Act: -0.0000

Data Index: 55140 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.3565. Min Act: -0.0000

Data Index: 193311 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1234856 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.3944. Min Act: -0.0000

Data Index: 316112 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4170. Min Act: -0.0000

Data Index: 512707 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4171. Min Act: -0.0000

Data Index: 137644 (C4 (Web Text))

Max Activating Token Index: 752