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

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

Neuron 2801 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: 1.4150. Min Range: -1.4150

Max Act: 1.4150. Min Act: -0.0003

Data Index: 464214 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.1822. Min Act: -0.0003

Data Index: 830493 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.2702. Min Act: -0.0003

Data Index: 980845 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.1511. Min Act: -0.0003

Data Index: 33530 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0254. Min Act: -0.0003

Data Index: 1133943 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0511. Min Act: -0.0003

Data Index: 733834 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.2224. Min Act: -0.0003

Data Index: 362959 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0952. Min Act: -0.0003

Data Index: 872783 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0482. Min Act: -0.0003

Data Index: 1160276 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9053. Min Act: -0.0003

Data Index: 484102 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9686. Min Act: -0.0003

Data Index: 447033 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0511. Min Act: -0.0003

Data Index: 235438 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9724. Min Act: -0.0003

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9867. Min Act: -0.0003

Data Index: 70283 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9491. Min Act: -0.0003

Data Index: 515001 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.4150. Min Range: -1.4150

Max Act: 1.0418. Min Act: -0.0003

Data Index: 163637 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9946. Min Act: -0.0003

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9478. Min Act: -0.0003

Data Index: 231201 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.8310. Min Act: -0.0003

Data Index: 1052715 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.4150. Min Range: -1.4150

Max Act: 0.9306. Min Act: -0.0003

Data Index: 336450 (C4 (Web Text))

Max Activating Token Index: 210