Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 203 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5279. Min Act: -0.0004

Data Index: 1189995 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5162. Min Act: -0.0004

Data Index: 1307613 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5378. Min Act: -0.0004

Data Index: 652881 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5650. Min Act: -0.0004

Data Index: 796069 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5266. Min Act: -0.0004

Data Index: 824662 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5196. Min Act: -0.0004

Data Index: 361740 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5536. Min Act: -0.0004

Data Index: 808296 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5413. Min Act: -0.0004

Data Index: 910824 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.6048. Min Act: -0.0004

Data Index: 896927 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5095. Min Act: -0.0004

Data Index: 582638 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5123. Min Act: -0.0004

Data Index: 836097 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5185. Min Act: -0.0004

Data Index: 399913 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4993. Min Act: -0.0004

Data Index: 183914 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5200. Min Act: -0.0004

Data Index: 196360 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5186. Min Act: -0.0004

Data Index: 179323 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5186. Min Act: -0.0004

Data Index: 320577 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5187. Min Act: -0.0004

Data Index: 1218816 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5017. Min Act: -0.0004

Data Index: 505493 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5158. Min Act: -0.0004

Data Index: 26957 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5175. Min Act: -0.0004

Data Index: 703692 (C4 (Web Text))

Max Activating Token Index: 745