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

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

Neuron 3312 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1326629 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1122717 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5135. Min Act: -0.0000

Data Index: 544354 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5405. Min Act: -0.0000

Data Index: 444538 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1181103 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4717. Min Act: -0.0000

Data Index: 846513 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5114. Min Act: -0.0000

Data Index: 938953 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4766. Min Act: -0.0000

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4738. Min Act: -0.0000

Data Index: 103704 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4323. Min Act: -0.0000

Data Index: 924826 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.3992. Min Act: -0.0000

Data Index: 802817 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4201. Min Act: -0.0000

Data Index: 92981 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4250. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4162. Min Act: -0.0000

Data Index: 298886 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4112. Min Act: -0.0000

Data Index: 181210 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.3901. Min Act: -0.0000

Data Index: 377554 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1350561 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.3969. Min Act: -0.0000

Data Index: 433918 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1338047 (C4 (Web Text))

Max Activating Token Index: 507