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

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

Neuron 2840 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6207. Min Act: -0.0001

Data Index: 218986 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.7383. Min Act: -0.0001

Data Index: 1124983 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6496. Min Act: -0.0001

Data Index: 844765 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5632. Min Act: -0.0001

Data Index: 1409293 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4222. Min Act: -0.0001

Data Index: 1059026 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1395037 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6408. Min Act: -0.0001

Data Index: 279108 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6309. Min Act: -0.0001

Data Index: 952301 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4149. Min Act: -0.0001

Data Index: 761655 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4467. Min Act: -0.0001

Data Index: 729419 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5152. Min Act: -0.0001

Data Index: 443074 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5171. Min Act: -0.0001

Data Index: 18667 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5515. Min Act: -0.0001

Data Index: 1269084 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5058. Min Act: -0.0001

Data Index: 132244 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4185. Min Act: -0.0001

Data Index: 556823 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2788. Min Act: -0.0001

Data Index: 884029 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1288211 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3959. Min Act: -0.0001

Data Index: 1325608 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2439. Min Act: -0.0001

Data Index: 1505601 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3026. Min Act: -0.0001

Data Index: 141209 (C4 (Web Text))

Max Activating Token Index: 270