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

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

Neuron 209 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.7043. Min Act: -0.0001

Data Index: 953217 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6322. Min Act: -0.0001

Data Index: 567130 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6164. Min Act: -0.0001

Data Index: 1305377 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6605. Min Act: -0.0001

Data Index: 217501 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6637. Min Act: -0.0001

Data Index: 1090765 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.5339. Min Act: -0.0001

Data Index: 132977 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.5727. Min Act: -0.0001

Data Index: 659592 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.4724. Min Act: -0.0001

Data Index: 1063290 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.4585. Min Act: -0.0001

Data Index: 1021207 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.4265. Min Act: -0.0001

Data Index: 23960 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.4210. Min Act: -0.0001

Data Index: 672449 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.3112. Min Act: -0.0001

Data Index: 101111 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.3610. Min Act: -0.0001

Data Index: 46892 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.4056. Min Act: -0.0001

Data Index: 565491 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.2413. Min Act: -0.0001

Data Index: 171800 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.3356. Min Act: -0.0001

Data Index: 1256147 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.3084. Min Act: -0.0001

Data Index: 1058125 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.1936. Min Act: -0.0001

Data Index: 393246 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.3034. Min Act: -0.0001

Data Index: 890671 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.2173. Min Act: -0.0001

Data Index: 3155 (C4 (Web Text))

Max Activating Token Index: 529