Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2946 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.8077. Min Act: -0.0000

Data Index: 381873 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.7004. Min Act: -0.0000

Data Index: 924645 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1332346 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1578347 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6464. Min Act: -0.0000

Data Index: 552880 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6328. Min Act: -0.0000

Data Index: 181776 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6413. Min Act: -0.0000

Data Index: 954076 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6332. Min Act: -0.0000

Data Index: 53842 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5834. Min Act: -0.0000

Data Index: 346927 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6018. Min Act: -0.0000

Data Index: 897070 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6682. Min Act: -0.0000

Data Index: 959750 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6229. Min Act: -0.0000

Data Index: 782485 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1584051 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1216251 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1278948 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5633. Min Act: -0.0000

Data Index: 245573 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5757. Min Act: -0.0000

Data Index: 762396 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1377488 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5657. Min Act: -0.0000

Data Index: 427974 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5873. Min Act: -0.0000

Data Index: 65034 (C4 (Web Text))

Max Activating Token Index: 486