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

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

Neuron 2649 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0000

Data Index: 819132 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0317. Min Act: -0.0000

Data Index: 639412 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0265. Min Act: -0.0000

Data Index: 438016 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0218. Min Act: -0.0000

Data Index: 945145 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0212. Min Act: -0.0000

Data Index: 297228 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0213. Min Act: -0.0000

Data Index: 953881 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0213. Min Act: -0.0000

Data Index: 430324 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1204341 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0168. Min Act: -0.0000

Data Index: 184417 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0204. Min Act: -0.0000

Data Index: 664491 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0185. Min Act: -0.0000

Data Index: 862031 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0191. Min Act: -0.0000

Data Index: 493082 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0198. Min Act: -0.0000

Data Index: 38025 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0168. Min Act: -0.0000

Data Index: 276541 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0169. Min Act: -0.0000

Data Index: 554213 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0148. Min Act: -0.0000

Data Index: 959119 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0185. Min Act: -0.0000

Data Index: 734403 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0183. Min Act: -0.0000

Data Index: 837278 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0189. Min Act: -0.0000

Data Index: 113586 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0161. Min Act: -0.0000

Data Index: 1065525 (C4 (Web Text))

Max Activating Token Index: 460