Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2673. Min Act: -0.0003

Data Index: 682078 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2739. Min Act: -0.0003

Data Index: 342718 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2462. Min Act: -0.0003

Data Index: 80867 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2521. Min Act: -0.0003

Data Index: 25521 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2274. Min Act: -0.0003

Data Index: 1153825 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2214. Min Act: -0.0003

Data Index: 975214 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2459. Min Act: -0.0003

Data Index: 226808 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2267. Min Act: -0.0003

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2294. Min Act: -0.0003

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2287. Min Act: -0.0003

Data Index: 51270 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2257. Min Act: -0.0003

Data Index: 801663 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2126. Min Act: -0.0003

Data Index: 317780 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2148. Min Act: -0.0003

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2205. Min Act: -0.0003

Data Index: 610142 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2117. Min Act: -0.0003

Data Index: 1132954 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2325. Min Act: -0.0003

Data Index: 113470 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2237. Min Act: -0.0003

Data Index: 832407 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2133. Min Act: -0.0003

Data Index: 145620 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2107. Min Act: -0.0003

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2036. Min Act: -0.0003

Data Index: 958596 (C4 (Web Text))

Max Activating Token Index: 705