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

Dataset: The Pile

Neuron 3114 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0000

Data Index: 229254 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1934956 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1213. Min Act: -0.0000

Data Index: 91636 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1115. Min Act: -0.0000

Data Index: 642074 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1557534 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1119. Min Act: -0.0000

Data Index: 971225 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1948579 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1888995 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0961. Min Act: -0.0000

Data Index: 10256 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1016. Min Act: -0.0000

Data Index: 41311 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0941. Min Act: -0.0000

Data Index: 189726 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0806. Min Act: -0.0000

Data Index: 271144 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1813860 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1325095 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1830059 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0890. Min Act: -0.0000

Data Index: 68408 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0911. Min Act: -0.0000

Data Index: 499041 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0828. Min Act: -0.0000

Data Index: 16134 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1192731 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1571955 (The Pile)

Max Activating Token Index: 124