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

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

Neuron 4001 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.9423. Min Act: -0.0000

Data Index: 594110 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.6062. Min Act: -0.0000

Data Index: 100726 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.4894. Min Act: -0.0000

Data Index: 732652 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.9230. Min Act: -0.0000

Data Index: 154228 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7428. Min Act: -0.0001

Data Index: 665606 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7188. Min Act: -0.0000

Data Index: 705354 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7027. Min Act: -0.0000

Data Index: 903234 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.6949. Min Act: -0.0000

Data Index: 1022588 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7706. Min Act: -0.0000

Data Index: 234554 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.8086. Min Act: -0.0000

Data Index: 1044399 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.4210. Min Act: -0.0001

Data Index: 290743 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.4077. Min Act: -0.0000

Data Index: 291413 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.4966. Min Act: -0.0000

Data Index: 433429 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7763. Min Act: -0.0000

Data Index: 874290 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.3454. Min Act: -0.0000

Data Index: 1069998 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.3327. Min Act: -0.0000

Data Index: 829730 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.4460. Min Act: -0.0000

Data Index: 681605 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.1020. Min Act: -0.0000

Data Index: 545319 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.0549. Min Act: -0.0000

Data Index: 923372 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.5380. Min Act: -0.0001

Data Index: 594329 (C4 (Web Text))

Max Activating Token Index: 920