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

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

Neuron 3406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1261090 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1320453 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6876. Min Act: -0.0000

Data Index: 384559 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6434. Min Act: -0.0000

Data Index: 775457 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6105. Min Act: -0.0000

Data Index: 303898 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6084. Min Act: -0.0000

Data Index: 678412 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1097309 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5735. Min Act: -0.0000

Data Index: 291714 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.6256. Min Act: -0.0000

Data Index: 63112 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5243. Min Act: -0.0000

Data Index: 184995 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1312539 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5090. Min Act: -0.0000

Data Index: 601528 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.4873. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5225. Min Act: -0.0000

Data Index: 803633 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.4911. Min Act: -0.0000

Data Index: 876324 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5178. Min Act: -0.0000

Data Index: 322643 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.4824. Min Act: -0.0000

Data Index: 799644 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.5627. Min Act: -0.0000

Data Index: 476212 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.4992. Min Act: -0.0000

Data Index: 362408 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.7953. Min Range: -0.7953

Max Act: 0.4663. Min Act: -0.0000

Data Index: 485847 (C4 (Web Text))

Max Activating Token Index: 222