Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2808 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0004

Data Index: 96398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0279. Min Act: -0.0004

Data Index: 906175 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0278. Min Act: -0.0004

Data Index: 561979 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0239. Min Act: -0.0004

Data Index: 520925 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0192. Min Act: -0.0004

Data Index: 1220872 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0252. Min Act: -0.0004

Data Index: 738173 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0235. Min Act: -0.0004

Data Index: 83940 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0239. Min Act: -0.0004

Data Index: 522086 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1138144 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0229. Min Act: -0.0004

Data Index: 226386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0250. Min Act: -0.0004

Data Index: 478443 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0233. Min Act: -0.0004

Data Index: 960822 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0236. Min Act: -0.0004

Data Index: 1210147 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0232. Min Act: -0.0004

Data Index: 628807 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0224. Min Act: -0.0004

Data Index: 1042138 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1226329 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0259. Min Act: -0.0004

Data Index: 103896 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0241. Min Act: -0.0004

Data Index: 534324 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0249. Min Act: -0.0004

Data Index: 621737 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0230. Min Act: -0.0004

Data Index: 763112 (C4 (Web Text))

Max Activating Token Index: 330