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

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

Neuron 3459 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 1069488 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 702965 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 262555 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 68451 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 80687 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 1093955 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 518712 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 933769 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 246358 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 177423 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1000106 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 668151 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 183603 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 603512 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 948971 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 668649 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 383208 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 353178 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1196779 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 987477 (C4 (Web Text))

Max Activating Token Index: 285