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

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

Neuron 5498 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1296. Min Range: -2.1296

Max Act: 2.1296. Min Act: 0.0000

Data Index: 551409 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 2.1296. Min Range: -2.1296

Max Act: 2.0067. Min Act: -0.0000

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.7971. Min Act: -0.0000

Data Index: 874157 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.8003. Min Act: -0.0000

Data Index: 415885 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.7622. Min Act: -0.0000

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.7173. Min Act: -0.0000

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.5378. Min Act: -0.0000

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.5562. Min Act: 0.0000

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4416. Min Act: -0.0000

Data Index: 499239 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4646. Min Act: -0.0000

Data Index: 27749 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1289048 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4503. Min Act: 0.0000

Data Index: 215741 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4416. Min Act: -0.0000

Data Index: 291987 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4231. Min Act: -0.0000

Data Index: 959513 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4004. Min Act: -0.0000

Data Index: 919443 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.3693. Min Act: -0.0000

Data Index: 670233 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.3504. Min Act: -0.0000

Data Index: 677588 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1329489 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.3289. Min Act: -0.0000

Data Index: 835269 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 2.1296. Min Range: -2.1296

Max Act: 1.3194. Min Act: -0.0000

Data Index: 401581 (C4 (Web Text))

Max Activating Token Index: 922