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

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

Neuron 5390 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.9077. Min Act: -0.0000

Data Index: 613249 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8224. Min Act: -0.0000

Data Index: 647552 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8234. Min Act: -0.0000

Data Index: 803659 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8155. Min Act: -0.0000

Data Index: 483495 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8142. Min Act: -0.0000

Data Index: 533232 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1205875 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1071396 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1085401 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7693. Min Act: -0.0000

Data Index: 777396 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7680. Min Act: -0.0000

Data Index: 704567 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7909. Min Act: -0.0000

Data Index: 503194 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7592. Min Act: -0.0000

Data Index: 640224 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8308. Min Act: -0.0000

Data Index: 522735 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7174. Min Act: -0.0000

Data Index: 917200 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7749. Min Act: -0.0000

Data Index: 834109 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1176485 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1341259 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1131977 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1114217 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7609. Min Act: -0.0000

Data Index: 893589 (C4 (Web Text))

Max Activating Token Index: 85