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

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

Neuron 3586 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.7385. Min Act: -0.0000

Data Index: 391659 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.7238. Min Act: -0.0000

Data Index: 301422 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1183562 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6261. Min Act: -0.0000

Data Index: 944492 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6381. Min Act: -0.0000

Data Index: 480776 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5979. Min Act: -0.0000

Data Index: 392228 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.6081. Min Act: -0.0000

Data Index: 706796 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5949. Min Act: -0.0000

Data Index: 223901 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5642. Min Act: -0.0000

Data Index: 444729 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5644. Min Act: -0.0000

Data Index: 235332 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5813. Min Act: -0.0000

Data Index: 144853 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5862. Min Act: -0.0000

Data Index: 326734 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5659. Min Act: -0.0000

Data Index: 816944 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1063250 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5331. Min Act: -0.0000

Data Index: 838394 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1221792 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1278305 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5639. Min Act: -0.0000

Data Index: 401538 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5801. Min Act: -0.0000

Data Index: 203985 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.7385. Min Range: -0.7385

Max Act: 0.5669. Min Act: -0.0000

Data Index: 232851 (C4 (Web Text))

Max Activating Token Index: 789