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

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

Neuron 5658 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2560. Min Act: -0.0000

Data Index: 727348 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2326. Min Act: -0.0000

Data Index: 411266 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2045. Min Act: -0.0001

Data Index: 323319 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2707. Min Act: -0.0000

Data Index: 15618 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2389. Min Act: -0.0000

Data Index: 23845 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2351. Min Act: -0.0000

Data Index: 978992 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2323. Min Act: -0.0000

Data Index: 377945 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1205842 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2345. Min Act: -0.0001

Data Index: 35872 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2121. Min Act: -0.0000

Data Index: 80946 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2242. Min Act: -0.0000

Data Index: 771541 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2259. Min Act: -0.0000

Data Index: 28777 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2199. Min Act: -0.0000

Data Index: 352710 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2146. Min Act: -0.0000

Data Index: 460779 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1144670 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2080. Min Act: -0.0000

Data Index: 648066 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1250798 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2094. Min Act: -0.0000

Data Index: 284220 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1938. Min Act: -0.0001

Data Index: 445000 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2016. Min Act: -0.0001

Data Index: 426486 (C4 (Web Text))

Max Activating Token Index: 14