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

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

Neuron 84 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.6868. Min Act: -0.0000

Data Index: 872084 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.3475. Min Act: -0.0000

Data Index: 151506 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.5244. Min Act: -0.0000

Data Index: 983353 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.3372. Min Act: -0.0000

Data Index: 813925 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.4543. Min Act: -0.0000

Data Index: 995824 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.3951. Min Act: -0.0000

Data Index: 1115383 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.2096. Min Act: -0.0000

Data Index: 1252936 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.3160. Min Act: -0.0000

Data Index: 1231212 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.0952. Min Act: -0.0000

Data Index: 1016262 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.2638. Min Act: -0.0000

Data Index: 878305 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.2117. Min Act: -0.0000

Data Index: 103140 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.1187. Min Act: -0.0000

Data Index: 915078 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.2758. Min Act: -0.0000

Data Index: 703978 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 5.6868. Min Range: -5.6868

Max Act: 5.0187. Min Act: -0.0000

Data Index: 734696 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 5.6868. Min Range: -5.6868

Max Act: 4.7002. Min Act: -0.0000

Data Index: 453146 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 5.6868. Min Range: -5.6868

Max Act: 4.5271. Min Act: -0.0000

Data Index: 113850 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 5.6868. Min Range: -5.6868

Max Act: 4.6439. Min Act: -0.0000

Data Index: 1278607 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 5.6868. Min Range: -5.6868

Max Act: 4.7835. Min Act: -0.0000

Data Index: 929874 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 5.6868. Min Range: -5.6868

Max Act: 4.5636. Min Act: -0.0000

Data Index: 752143 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 5.6868. Min Range: -5.6868

Max Act: 4.5099. Min Act: -0.0000

Data Index: 621460 (C4 (Web Text))

Max Activating Token Index: 257