Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1148 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.6927. Min Act: -0.0001

Data Index: 1094691 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.5490. Min Act: -0.0001

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.7221. Min Act: -0.0001

Data Index: 357411 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.5770. Min Act: -0.0001

Data Index: 927848 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.5028. Min Act: -0.0001

Data Index: 1203822 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4982. Min Act: -0.0002

Data Index: 274575 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.5056. Min Act: -0.0001

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4457. Min Act: -0.0001

Data Index: 95177 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4918. Min Act: -0.0001

Data Index: 1253181 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4746. Min Act: -0.0001

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4603. Min Act: -0.0002

Data Index: 1313560 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4376. Min Act: -0.0001

Data Index: 1085432 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4393. Min Act: -0.0001

Data Index: 156553 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.3635. Min Act: -0.0001

Data Index: 113470 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.3490. Min Act: -0.0001

Data Index: 1227350 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.3640. Min Act: -0.0002

Data Index: 1117716 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.3940. Min Act: -0.0002

Data Index: 1348624 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.3471. Min Act: -0.0001

Data Index: 915283 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.3473. Min Act: -0.0001

Data Index: 1238915 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.7221. Min Range: -1.7221

Max Act: 1.4295. Min Act: -0.0001

Data Index: 992062 (C4 (Web Text))

Max Activating Token Index: 213