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

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

Neuron 938 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.4597. Min Act: -0.0000

Data Index: 1176301 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.8156. Min Act: -0.0000

Data Index: 1212504 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.2916. Min Act: -0.0000

Data Index: 1149599 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.3684. Min Act: -0.0000

Data Index: 57829 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.5056. Min Act: -0.0000

Data Index: 113508 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.6633. Min Act: -0.0000

Data Index: 1085743 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.3038. Min Act: -0.0000

Data Index: 326732 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.4732. Min Act: -0.0000

Data Index: 552286 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.4379. Min Act: -0.0000

Data Index: 1356333 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.0906. Min Act: -0.0000

Data Index: 895407 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.0870. Min Act: -0.0000

Data Index: 569373 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.3906. Min Act: -0.0000

Data Index: 989227 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.2024. Min Act: -0.0000

Data Index: 259617 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.1563. Min Act: -0.0000

Data Index: 385835 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.3043. Min Act: -0.0000

Data Index: 899914 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.2679. Min Act: -0.0000

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 8.8156. Min Range: -8.8156

Max Act: 7.9387. Min Act: -0.0000

Data Index: 675104 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 8.8156. Min Range: -8.8156

Max Act: 8.2074. Min Act: -0.0000

Data Index: 1324913 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 8.8156. Min Range: -8.8156

Max Act: 7.9637. Min Act: -0.0000

Data Index: 1009188 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 8.8156. Min Range: -8.8156

Max Act: 7.9539. Min Act: -0.0000

Data Index: 775659 (C4 (Web Text))

Max Activating Token Index: 209