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

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

Neuron 170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1476504 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1560163 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0434. Min Act: -0.0002

Data Index: 103602 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1214924 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1427140 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1269676 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0392. Min Act: -0.0002

Data Index: 63962 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0359. Min Act: -0.0002

Data Index: 222912 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0369. Min Act: -0.0002

Data Index: 847256 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0375. Min Act: -0.0002

Data Index: 252250 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0372. Min Act: -0.0002

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1528657 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0358. Min Act: -0.0002

Data Index: 794303 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1544005 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1410127 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1488623 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1602716 (Python Code)

Max Activating Token Index: 861

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0331. Min Act: -0.0002

Data Index: 939459 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0355. Min Act: -0.0002

Data Index: 97409 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1643053 (Python Code)

Max Activating Token Index: 41