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

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

Neuron 2530 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.4144. Min Act: -0.0002

Data Index: 585227 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3800. Min Act: -0.0002

Data Index: 349146 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3581. Min Act: -0.0002

Data Index: 619946 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3590. Min Act: -0.0002

Data Index: 115808 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3573. Min Act: -0.0002

Data Index: 52058 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3568. Min Act: -0.0002

Data Index: 1132415 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3489. Min Act: -0.0002

Data Index: 764233 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3488. Min Act: -0.0002

Data Index: 617950 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3446. Min Act: -0.0002

Data Index: 269825 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3316. Min Act: -0.0002

Data Index: 283676 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3262. Min Act: -0.0002

Data Index: 262705 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3142. Min Act: -0.0002

Data Index: 690861 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3096. Min Act: -0.0002

Data Index: 305416 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3158. Min Act: -0.0002

Data Index: 264868 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3033. Min Act: -0.0002

Data Index: 787390 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3103. Min Act: -0.0002

Data Index: 1222132 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.2995. Min Act: -0.0002

Data Index: 1149053 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3092. Min Act: -0.0002

Data Index: 341732 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3044. Min Act: -0.0002

Data Index: 638221 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.4144. Min Range: -0.4144

Max Act: 0.3135. Min Act: -0.0002

Data Index: 683046 (C4 (Web Text))

Max Activating Token Index: 710