Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3194 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2863. Min Act: -0.0001

Data Index: 895775 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2558. Min Act: -0.0000

Data Index: 677769 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2495. Min Act: -0.0000

Data Index: 91119 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2226. Min Act: -0.0001

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2433. Min Act: -0.0001

Data Index: 88343 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2241. Min Act: -0.0000

Data Index: 655306 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2216. Min Act: -0.0001

Data Index: 88192 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2299. Min Act: -0.0000

Data Index: 53177 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1042256 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2186. Min Act: -0.0000

Data Index: 173097 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2249. Min Act: -0.0000

Data Index: 170008 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1159141 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2205. Min Act: -0.0000

Data Index: 553183 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2045. Min Act: -0.0001

Data Index: 303971 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2389. Min Act: -0.0000

Data Index: 93255 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2107. Min Act: -0.0000

Data Index: 775541 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2020. Min Act: -0.0000

Data Index: 686116 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2032. Min Act: -0.0000

Data Index: 785318 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.2863. Min Range: -0.2863

Max Act: 0.2100. Min Act: -0.0001

Data Index: 143787 (C4 (Web Text))

Max Activating Token Index: 185