Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1283 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3999. Min Act: -0.0002

Data Index: 1201846 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3425. Min Act: -0.0002

Data Index: 934058 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3362. Min Act: -0.0002

Data Index: 758947 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3372. Min Act: -0.0002

Data Index: 44468 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3233. Min Act: -0.0002

Data Index: 1106066 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3139. Min Act: -0.0002

Data Index: 92780 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3151. Min Act: -0.0002

Data Index: 473786 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3158. Min Act: -0.0002

Data Index: 311206 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3112. Min Act: -0.0002

Data Index: 149915 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3188. Min Act: -0.0002

Data Index: 1147574 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3068. Min Act: -0.0002

Data Index: 548015 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3030. Min Act: -0.0002

Data Index: 1048353 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3078. Min Act: -0.0002

Data Index: 181607 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3008. Min Act: -0.0002

Data Index: 632168 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3051. Min Act: -0.0002

Data Index: 1165888 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3011. Min Act: -0.0002

Data Index: 1220252 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.2986. Min Act: -0.0002

Data Index: 27223 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3039. Min Act: -0.0002

Data Index: 1325645 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.2963. Min Act: -0.0002

Data Index: 449233 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.2999. Min Act: -0.0002

Data Index: 236292 (C4 (Web Text))

Max Activating Token Index: 500