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

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

Neuron 4765 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: 0.0341. Min Range: -0.0341

Max Act: 0.0341. Min Act: -0.0003

Data Index: 749520 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0340. Min Act: -0.0003

Data Index: 203045 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0325. Min Act: -0.0002

Data Index: 335120 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0330. Min Act: -0.0003

Data Index: 185739 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0329. Min Act: -0.0003

Data Index: 961676 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0313. Min Act: -0.0003

Data Index: 512354 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1243405 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0290. Min Act: -0.0002

Data Index: 591771 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0300. Min Act: -0.0003

Data Index: 565600 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1301807 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0293. Min Act: -0.0003

Data Index: 155399 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0297. Min Act: -0.0002

Data Index: 887230 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0295. Min Act: -0.0003

Data Index: 606915 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0282. Min Act: -0.0002

Data Index: 30227 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1249687 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0287. Min Act: -0.0002

Data Index: 905608 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0286. Min Act: -0.0002

Data Index: 355104 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1111097 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0279. Min Act: -0.0003

Data Index: 124248 (C4 (Web Text))

Max Activating Token Index: 316