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

Dataset: The Pile

Neuron 2358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2333. Min Act: -0.0000

Data Index: 617141 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1924105 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2388. Min Act: -0.0000

Data Index: 971442 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2229. Min Act: -0.0000

Data Index: 916216 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1400167 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2224. Min Act: -0.0000

Data Index: 724152 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2209. Min Act: -0.0000

Data Index: 26294 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2367. Min Act: -0.0000

Data Index: 212224 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1964994 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2258. Min Act: -0.0000

Data Index: 143660 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1200206 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1612617 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1402141 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1979. Min Act: -0.0000

Data Index: 527524 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1528191 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2124. Min Act: -0.0000

Data Index: 855518 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1942868 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1187160 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1935. Min Act: -0.0000

Data Index: 321587 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2143. Min Act: -0.0000

Data Index: 257129 (The Pile)

Max Activating Token Index: 189