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

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

Neuron 1127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.3349. Min Act: -0.0001

Data Index: 793406 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.1240. Min Act: -0.0001

Data Index: 510519 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.1590. Min Act: -0.0001

Data Index: 574013 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.0724. Min Act: -0.0001

Data Index: 678902 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.0383. Min Act: -0.0001

Data Index: 1524128 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1150485 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9906. Min Act: -0.0001

Data Index: 1184785 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.8976. Min Act: -0.0002

Data Index: 1417696 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9579. Min Act: -0.0001

Data Index: 175309 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9215. Min Act: -0.0001

Data Index: 1107257 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9502. Min Act: -0.0002

Data Index: 1210915 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9396. Min Act: -0.0001

Data Index: 1268683 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.0492. Min Act: -0.0002

Data Index: 280134 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.3349. Min Range: -1.3349

Max Act: 1.0505. Min Act: -0.0002

Data Index: 992552 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.8855. Min Act: -0.0002

Data Index: 522477 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.9650. Min Act: -0.0001

Data Index: 110605 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.8239. Min Act: -0.0001

Data Index: 848271 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1641493 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1413078 (Python Code)

Max Activating Token Index: 751

Text #19

Max Range: 1.3349. Min Range: -1.3349

Max Act: 0.7660. Min Act: -0.0001

Data Index: 1379932 (Python Code)

Max Activating Token Index: 795