Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0761. Min Range: -1.0761

Max Act: 1.0720. Min Act: -0.0001

Data Index: 848311 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.0761. Min Range: -1.0761

Max Act: 1.0445. Min Act: -0.0001

Data Index: 872390 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.0761. Min Range: -1.0761

Max Act: 1.0761. Min Act: -0.0001

Data Index: 1032929 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9811. Min Act: -0.0001

Data Index: 1079409 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9813. Min Act: -0.0001

Data Index: 952364 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9385. Min Act: -0.0001

Data Index: 381238 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8677. Min Act: -0.0001

Data Index: 1050555 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9156. Min Act: -0.0001

Data Index: 1357678 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8441. Min Act: -0.0001

Data Index: 1191830 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9625. Min Act: -0.0001

Data Index: 25746 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8783. Min Act: -0.0001

Data Index: 101444 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8751. Min Act: -0.0001

Data Index: 694221 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9243. Min Act: -0.0001

Data Index: 819934 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8619. Min Act: -0.0001

Data Index: 106122 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8349. Min Act: -0.0001

Data Index: 187966 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1348544 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7934. Min Act: -0.0001

Data Index: 410821 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1254837 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8311. Min Act: -0.0001

Data Index: 631336 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8263. Min Act: -0.0001

Data Index: 902346 (C4 (Web Text))

Max Activating Token Index: 632