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

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

Neuron 3003 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.3829. Min Act: -0.0000

Data Index: 121360 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.4657. Min Act: -0.0000

Data Index: 1621776 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.9925. Min Act: -0.0000

Data Index: 1265930 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.6523. Min Act: -0.0000

Data Index: 83516 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.7964. Min Act: -0.0000

Data Index: 261746 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.9373. Min Act: -0.0000

Data Index: 789418 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.7544. Min Act: -0.0000

Data Index: 1208015 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.7181. Min Act: -0.0000

Data Index: 721723 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.8688. Min Act: -0.0000

Data Index: 940979 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 4.4657. Min Range: -4.4657

Max Act: 4.0159. Min Act: -0.0000

Data Index: 374786 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.8161. Min Act: -0.0000

Data Index: 1348072 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.7823. Min Act: -0.0000

Data Index: 537412 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.5874. Min Act: -0.0000

Data Index: 174425 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.7802. Min Act: -0.0000

Data Index: 588270 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.9182. Min Act: -0.0000

Data Index: 1312574 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.9056. Min Act: -0.0000

Data Index: 1053994 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.5222. Min Act: -0.0000

Data Index: 820484 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.6554. Min Act: -0.0000

Data Index: 297577 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.8490. Min Act: -0.0000

Data Index: 317631 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 4.4657. Min Range: -4.4657

Max Act: 3.6579. Min Act: -0.0000

Data Index: 1310452 (C4 (Web Text))

Max Activating Token Index: 158