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

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

Neuron 4148 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0333. Min Act: -0.0002

Data Index: 399791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0002

Data Index: 755617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0296. Min Act: -0.0002

Data Index: 665131 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1335122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0314. Min Act: -0.0002

Data Index: 598870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1537492 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0272. Min Act: -0.0002

Data Index: 526830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0252. Min Act: -0.0002

Data Index: 811834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0266. Min Act: -0.0002

Data Index: 2535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1070827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0260. Min Act: -0.0002

Data Index: 993308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1447099 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0235. Min Act: -0.0002

Data Index: 567708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1600039 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1181006 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1069872 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1235145 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1479915 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1543045 (Python Code)

Max Activating Token Index: 969

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0218. Min Act: -0.0002

Data Index: 878085 (C4 (Web Text))

Max Activating Token Index: 36