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

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

Neuron 1428 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.9171. Min Act: -0.0001

Data Index: 1312326 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.8035. Min Act: -0.0000

Data Index: 594279 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.7489. Min Act: -0.0001

Data Index: 900599 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.5400. Min Act: -0.0001

Data Index: 1105347 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.5903. Min Act: -0.0001

Data Index: 1191522 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3946. Min Act: -0.0001

Data Index: 668830 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3695. Min Act: -0.0001

Data Index: 192043 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3714. Min Act: -0.0001

Data Index: 185618 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3970. Min Act: -0.0001

Data Index: 510951 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3952. Min Act: -0.0001

Data Index: 293557 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3019. Min Act: -0.0001

Data Index: 649878 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.3091. Min Act: -0.0001

Data Index: 564482 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.1658. Min Act: -0.0001

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.5191. Min Act: -0.0001

Data Index: 677642 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.2118. Min Act: -0.0001

Data Index: 222732 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.2572. Min Act: -0.0001

Data Index: 1305041 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.2324. Min Act: -0.0001

Data Index: 507005 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.1844. Min Act: -0.0000

Data Index: 285263 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.2688. Min Act: -0.0001

Data Index: 1084509 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.9171. Min Range: -1.9171

Max Act: 1.1974. Min Act: -0.0001

Data Index: 996770 (C4 (Web Text))

Max Activating Token Index: 939