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

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

Neuron 4955 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: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0003

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0357. Min Act: -0.0003

Data Index: 117070 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0321. Min Act: -0.0003

Data Index: 399649 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0317. Min Act: -0.0003

Data Index: 791283 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0308. Min Act: -0.0003

Data Index: 588661 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1114503 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0310. Min Act: -0.0002

Data Index: 358554 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1117849 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0310. Min Act: -0.0003

Data Index: 459861 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0311. Min Act: -0.0003

Data Index: 733958 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1307116 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0307. Min Act: -0.0003

Data Index: 511133 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0296. Min Act: -0.0003

Data Index: 30933 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0299. Min Act: -0.0002

Data Index: 771498 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1194191 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0310. Min Act: -0.0003

Data Index: 217946 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1213672 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1376771 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1208832 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0292. Min Act: -0.0003

Data Index: 364823 (C4 (Web Text))

Max Activating Token Index: 153