Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3826 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0002

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5767. Min Act: -0.0002

Data Index: 5491 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5706. Min Act: -0.0003

Data Index: 1328880 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4851. Min Act: -0.0003

Data Index: 570541 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4728. Min Act: -0.0003

Data Index: 1159520 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4575. Min Act: -0.0003

Data Index: 229176 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4508. Min Act: -0.0002

Data Index: 488999 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4509. Min Act: -0.0003

Data Index: 888938 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4491. Min Act: -0.0002

Data Index: 443567 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4445. Min Act: -0.0002

Data Index: 808461 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4331. Min Act: -0.0002

Data Index: 62818 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4453. Min Act: -0.0003

Data Index: 273621 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4393. Min Act: -0.0002

Data Index: 69841 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4380. Min Act: -0.0003

Data Index: 1338961 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4338. Min Act: -0.0003

Data Index: 295859 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4344. Min Act: -0.0003

Data Index: 588179 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4303. Min Act: -0.0003

Data Index: 849649 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4247. Min Act: -0.0002

Data Index: 810190 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4334. Min Act: -0.0002

Data Index: 91701 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4178. Min Act: -0.0002

Data Index: 69697 (C4 (Web Text))

Max Activating Token Index: 234