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

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

Neuron 1093 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: 1.0384. Min Range: -1.0384

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1465223 (Python Code)

Max Activating Token Index: 411

Text #1

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9830. Min Act: -0.0000

Data Index: 319382 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9360. Min Act: -0.0000

Data Index: 102581 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8909. Min Act: -0.0000

Data Index: 265106 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9413. Min Act: -0.0000

Data Index: 500654 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8423. Min Act: -0.0000

Data Index: 495430 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8713. Min Act: -0.0000

Data Index: 530371 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9419. Min Act: -0.0000

Data Index: 459855 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1184216 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8548. Min Act: -0.0000

Data Index: 741683 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1447001 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1292327 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8341. Min Act: -0.0000

Data Index: 199098 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1080131 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8673. Min Act: -0.0000

Data Index: 972344 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1617345 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1164616 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8351. Min Act: -0.0000

Data Index: 544234 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1161475 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7920. Min Act: -0.0000

Data Index: 861371 (C4 (Web Text))

Max Activating Token Index: 2