Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3778 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0003

Data Index: 30053 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0441. Min Act: -0.0003

Data Index: 486118 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0384. Min Act: -0.0003

Data Index: 629675 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1162769 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0357. Min Act: -0.0003

Data Index: 131583 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0342. Min Act: -0.0003

Data Index: 220712 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1156357 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1158967 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0323. Min Act: -0.0003

Data Index: 702502 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0330. Min Act: -0.0003

Data Index: 481959 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1147068 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1017247 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0292. Min Act: -0.0003

Data Index: 883947 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0305. Min Act: -0.0003

Data Index: 815700 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0296. Min Act: -0.0003

Data Index: 69636 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1060207 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0285. Min Act: -0.0003

Data Index: 743368 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0287. Min Act: -0.0003

Data Index: 576877 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0290. Min Act: -0.0003

Data Index: 170746 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0288. Min Act: -0.0003

Data Index: 6721 (C4 (Web Text))

Max Activating Token Index: 388