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

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

Neuron 5013 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2248. Min Act: -0.0001

Data Index: 977844 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2308. Min Act: -0.0001

Data Index: 661039 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1359246 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2238. Min Act: -0.0001

Data Index: 194081 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2279. Min Act: -0.0001

Data Index: 733807 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2297. Min Act: -0.0001

Data Index: 193606 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1017189 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1185828 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2157. Min Act: -0.0001

Data Index: 260836 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1233744 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1007514 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2023. Min Act: -0.0001

Data Index: 515151 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2092. Min Act: -0.0001

Data Index: 42424 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2074. Min Act: -0.0001

Data Index: 653436 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2157. Min Act: -0.0001

Data Index: 602496 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2026. Min Act: -0.0001

Data Index: 430286 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2001. Min Act: -0.0001

Data Index: 5611 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1050301 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2067. Min Act: -0.0001

Data Index: 300974 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.2347. Min Range: -0.2347

Max Act: 0.2064. Min Act: -0.0001

Data Index: 655388 (C4 (Web Text))

Max Activating Token Index: 121