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

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

Neuron 3890 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.7197. Min Act: -0.0003

Data Index: 405901 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6198. Min Act: -0.0003

Data Index: 402129 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5772. Min Act: -0.0003

Data Index: 1039599 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5668. Min Act: -0.0003

Data Index: 183850 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5644. Min Act: -0.0003

Data Index: 151158 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5348. Min Act: -0.0003

Data Index: 1281676 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5177. Min Act: -0.0003

Data Index: 951002 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5280. Min Act: -0.0002

Data Index: 296175 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5431. Min Act: -0.0003

Data Index: 1143488 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5433. Min Act: -0.0003

Data Index: 25236 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5211. Min Act: -0.0003

Data Index: 7725 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4982. Min Act: -0.0003

Data Index: 654358 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5138. Min Act: -0.0003

Data Index: 963256 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5031. Min Act: -0.0002

Data Index: 1296960 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4783. Min Act: -0.0003

Data Index: 943597 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4788. Min Act: -0.0003

Data Index: 214168 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4894. Min Act: -0.0003

Data Index: 396138 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4570. Min Act: -0.0003

Data Index: 691584 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4822. Min Act: -0.0003

Data Index: 640881 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4835. Min Act: -0.0003

Data Index: 928358 (C4 (Web Text))

Max Activating Token Index: 300