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

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

Neuron 563 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2378. Min Act: -0.0002

Data Index: 522252 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2290. Min Act: -0.0002

Data Index: 1266872 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2234. Min Act: -0.0002

Data Index: 609960 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2176. Min Act: -0.0002

Data Index: 1329633 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2167. Min Act: -0.0002

Data Index: 845291 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2210. Min Act: -0.0002

Data Index: 275242 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2256. Min Act: -0.0002

Data Index: 1255917 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2334. Min Act: -0.0002

Data Index: 393423 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2081. Min Act: -0.0002

Data Index: 319072 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2154. Min Act: -0.0002

Data Index: 1083813 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2286. Min Act: -0.0002

Data Index: 556005 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2366. Min Act: -0.0002

Data Index: 259094 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2205. Min Act: -0.0002

Data Index: 161620 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2145. Min Act: -0.0002

Data Index: 913323 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2284. Min Act: -0.0002

Data Index: 615517 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2203. Min Act: -0.0002

Data Index: 714688 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2125. Min Act: -0.0002

Data Index: 788905 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2128. Min Act: -0.0002

Data Index: 125660 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2173. Min Act: -0.0002

Data Index: 160243 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.2378. Min Range: -0.2378

Max Act: 0.2111. Min Act: -0.0002

Data Index: 1099544 (C4 (Web Text))

Max Activating Token Index: 66