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

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

Neuron 18 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: 0.0303. Min Range: -0.0303

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1016071 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0003

Data Index: 481036 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0003

Data Index: 114062 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0003

Data Index: 4730 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1214781 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0273. Min Act: -0.0003

Data Index: 194512 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0003

Data Index: 4248 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1283439 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0271. Min Act: -0.0003

Data Index: 214886 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0271. Min Act: -0.0003

Data Index: 270994 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0003

Data Index: 620741 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0264. Min Act: -0.0003

Data Index: 184426 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0003

Data Index: 544055 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1184099 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0273. Min Act: -0.0003

Data Index: 611749 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0258. Min Act: -0.0003

Data Index: 49895 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0262. Min Act: -0.0003

Data Index: 71114 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0256. Min Act: -0.0003

Data Index: 392235 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1022923 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1252615 (C4 (Web Text))

Max Activating Token Index: 254