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

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

Neuron 4967 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: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1319205 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1189215 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0372. Min Act: -0.0000

Data Index: 400121 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0371. Min Act: -0.0000

Data Index: 453893 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0386. Min Act: -0.0000

Data Index: 207115 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0359. Min Act: -0.0000

Data Index: 319124 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0342. Min Act: 0.0000

Data Index: 962500 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0351. Min Act: -0.0000

Data Index: 860847 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0348. Min Act: -0.0000

Data Index: 408474 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0325. Min Act: 0.0000

Data Index: 46825 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0347. Min Act: -0.0000

Data Index: 968358 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0347. Min Act: -0.0000

Data Index: 112874 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0339. Min Act: -0.0000

Data Index: 776406 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0340. Min Act: -0.0000

Data Index: 710139 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0313. Min Act: -0.0000

Data Index: 404271 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0314. Min Act: -0.0000

Data Index: 662550 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1149323 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0344. Min Act: 0.0000

Data Index: 1354767 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0330. Min Act: -0.0000

Data Index: 366205 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0323. Min Act: 0.0000

Data Index: 229721 (C4 (Web Text))

Max Activating Token Index: 212