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

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

Neuron 992 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9906. Min Act: -0.0000

Data Index: 576363 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.0079. Min Range: -1.0079

Max Act: 1.0079. Min Act: -0.0000

Data Index: 368227 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8129. Min Act: -0.0000

Data Index: 84213 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1311594 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8928. Min Act: -0.0000

Data Index: 213378 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8132. Min Act: -0.0000

Data Index: 415215 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7711. Min Act: -0.0000

Data Index: 254349 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8332. Min Act: -0.0000

Data Index: 178876 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8179. Min Act: -0.0000

Data Index: 937093 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7879. Min Act: -0.0000

Data Index: 407854 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7401. Min Act: -0.0000

Data Index: 2402 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7588. Min Act: -0.0000

Data Index: 8101 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7690. Min Act: -0.0000

Data Index: 209914 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1319477 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7535. Min Act: -0.0000

Data Index: 295406 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1153928 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7250. Min Act: -0.0000

Data Index: 243846 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1171994 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6892. Min Act: -0.0000

Data Index: 482349 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6875. Min Act: -0.0000

Data Index: 421224 (C4 (Web Text))

Max Activating Token Index: 728