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

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

Neuron 2312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2448. Min Act: -0.0002

Data Index: 1216745 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2368. Min Act: -0.0002

Data Index: 77935 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2337. Min Act: -0.0002

Data Index: 471118 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2329. Min Act: -0.0002

Data Index: 461157 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2227. Min Act: -0.0002

Data Index: 420968 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2089. Min Act: -0.0002

Data Index: 166034 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2255. Min Act: -0.0002

Data Index: 1090655 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2173. Min Act: -0.0002

Data Index: 1092740 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2131. Min Act: -0.0002

Data Index: 818224 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2140. Min Act: -0.0002

Data Index: 551161 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2181. Min Act: -0.0002

Data Index: 71793 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2050. Min Act: -0.0002

Data Index: 85650 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1934. Min Act: -0.0002

Data Index: 103171 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1910. Min Act: -0.0002

Data Index: 520690 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1743. Min Act: -0.0002

Data Index: 556607 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1947. Min Act: -0.0002

Data Index: 348889 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1877. Min Act: -0.0002

Data Index: 170286 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1852. Min Act: -0.0002

Data Index: 203116 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1902. Min Act: -0.0002

Data Index: 298256 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2118. Min Act: -0.0002

Data Index: 1038541 (C4 (Web Text))

Max Activating Token Index: 245