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

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

Neuron 4061 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: 0.6188. Min Range: -0.6188

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1261769 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.6166. Min Act: 0.0000

Data Index: 613897 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.6006. Min Act: -0.0000

Data Index: 478647 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.6188. Min Act: 0.0000

Data Index: 373590 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5815. Min Act: -0.0000

Data Index: 75655 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5170. Min Act: -0.0000

Data Index: 951152 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5237. Min Act: -0.0000

Data Index: 384884 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5192. Min Act: -0.0000

Data Index: 49563 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5218. Min Act: -0.0000

Data Index: 95443 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5191. Min Act: -0.0000

Data Index: 797923 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5238. Min Act: -0.0000

Data Index: 690127 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4601. Min Act: -0.0000

Data Index: 613850 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4911. Min Act: -0.0000

Data Index: 266027 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1070503 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1000457 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4496. Min Act: 0.0000

Data Index: 241169 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4774. Min Act: -0.0000

Data Index: 540912 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4652. Min Act: -0.0000

Data Index: 302432 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4860. Min Act: -0.0000

Data Index: 223697 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4699. Min Act: -0.0000

Data Index: 979748 (C4 (Web Text))

Max Activating Token Index: 45