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

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

Neuron 3572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3336. Min Range: -2.3336

Max Act: 2.3336. Min Act: -0.0000

Data Index: 398010 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 2.3336. Min Range: -2.3336

Max Act: 2.2238. Min Act: -0.0000

Data Index: 1469895 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 2.3336. Min Range: -2.3336

Max Act: 2.1606. Min Act: -0.0000

Data Index: 814973 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 2.3336. Min Range: -2.3336

Max Act: 2.0982. Min Act: -0.0000

Data Index: 849467 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1900 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9743. Min Act: -0.0000

Data Index: 910101 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9645. Min Act: -0.0000

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.3336. Min Range: -2.3336

Max Act: 2.0790. Min Act: -0.0000

Data Index: 194476 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9118. Min Act: -0.0000

Data Index: 1304629 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9782. Min Act: -0.0000

Data Index: 1183631 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9745. Min Act: -0.0000

Data Index: 35933 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 2.3336. Min Range: -2.3336

Max Act: 2.1011. Min Act: -0.0000

Data Index: 835204 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9810. Min Act: -0.0000

Data Index: 1252678 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9845. Min Act: -0.0000

Data Index: 272122 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9781. Min Act: -0.0000

Data Index: 964823 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9703. Min Act: -0.0000

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.8368. Min Act: -0.0000

Data Index: 244809 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9552. Min Act: -0.0000

Data Index: 839195 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9471. Min Act: -0.0000

Data Index: 1012712 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 2.3336. Min Range: -2.3336

Max Act: 1.9556. Min Act: -0.0000

Data Index: 1019715 (C4 (Web Text))

Max Activating Token Index: 531