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

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

Neuron 1346 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: 0.0584. Min Range: -0.0584

Max Act: 0.0565. Min Act: -0.0000

Data Index: 283101 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0000

Data Index: 971931 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0509. Min Act: -0.0000

Data Index: 543228 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0479. Min Act: -0.0000

Data Index: 570566 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0414. Min Act: -0.0000

Data Index: 705473 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0452. Min Act: -0.0000

Data Index: 784116 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0412. Min Act: -0.0000

Data Index: 113458 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0405. Min Act: -0.0000

Data Index: 966421 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1007266 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0396. Min Act: -0.0000

Data Index: 819258 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1284604 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0371. Min Act: -0.0000

Data Index: 734186 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0341. Min Act: -0.0000

Data Index: 514344 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0390. Min Act: -0.0000

Data Index: 305020 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0379. Min Act: -0.0000

Data Index: 560378 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1276828 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1387924 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0358. Min Act: -0.0000

Data Index: 930949 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0357. Min Act: -0.0000

Data Index: 6068 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0367. Min Act: -0.0000

Data Index: 710527 (C4 (Web Text))

Max Activating Token Index: 845