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

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

Neuron 3260 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: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1342642 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1104926 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0439. Min Act: -0.0002

Data Index: 710516 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0422. Min Act: -0.0002

Data Index: 256892 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0417. Min Act: -0.0002

Data Index: 314975 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0420. Min Act: -0.0002

Data Index: 225429 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1221944 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1014212 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0386. Min Act: -0.0002

Data Index: 895489 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0368. Min Act: -0.0002

Data Index: 803208 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0365. Min Act: -0.0002

Data Index: 13437 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0365. Min Act: -0.0002

Data Index: 542588 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1229146 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0350. Min Act: -0.0002

Data Index: 767701 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1323044 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0361. Min Act: -0.0002

Data Index: 671143 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0341. Min Act: -0.0002

Data Index: 819590 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0354. Min Act: -0.0002

Data Index: 605017 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0379. Min Act: -0.0002

Data Index: 661776 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0348. Min Act: -0.0002

Data Index: 752115 (C4 (Web Text))

Max Activating Token Index: 739