Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2349 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0283. Min Act: -0.0002

Data Index: 219920 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0002

Data Index: 860757 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0285. Min Act: -0.0002

Data Index: 984841 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1140141 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0278. Min Act: -0.0001

Data Index: 421556 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0278. Min Act: -0.0001

Data Index: 441923 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0269. Min Act: -0.0001

Data Index: 247374 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1250136 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0247. Min Act: -0.0001

Data Index: 998835 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0260. Min Act: -0.0002

Data Index: 373872 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1133700 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0198. Min Act: -0.0001

Data Index: 644218 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0230. Min Act: -0.0002

Data Index: 273641 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0241. Min Act: -0.0001

Data Index: 785654 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1501525 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0229. Min Act: -0.0002

Data Index: 150980 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0247. Min Act: -0.0001

Data Index: 809984 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0234. Min Act: -0.0001

Data Index: 902896 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0230. Min Act: -0.0002

Data Index: 812806 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0241. Min Act: -0.0001

Data Index: 274534 (C4 (Web Text))

Max Activating Token Index: 517