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

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

Neuron 354 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: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1153171 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0300. Min Act: -0.0003

Data Index: 39626 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0272. Min Act: -0.0003

Data Index: 842250 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0281. Min Act: -0.0003

Data Index: 380300 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0266. Min Act: -0.0003

Data Index: 332087 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0262. Min Act: -0.0003

Data Index: 765121 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0264. Min Act: -0.0003

Data Index: 879830 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0246. Min Act: -0.0003

Data Index: 423845 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0236. Min Act: -0.0002

Data Index: 762565 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0242. Min Act: -0.0003

Data Index: 905045 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1090064 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0232. Min Act: -0.0003

Data Index: 115464 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0233. Min Act: -0.0003

Data Index: 115082 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0238. Min Act: -0.0003

Data Index: 176479 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1017833 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1076733 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1177596 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1497361 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1385782 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1423287 (Python Code)

Max Activating Token Index: 1