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

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

Neuron 3547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.7322. Min Act: -0.0000

Data Index: 136046 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1227097 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1021334 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1033610 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1360. Min Act: -0.0000

Data Index: 388523 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.2377. Min Act: -0.0000

Data Index: 652233 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.0887. Min Act: -0.0000

Data Index: 682707 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1180837 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.2064. Min Act: -0.0000

Data Index: 54984 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.2141. Min Act: -0.0000

Data Index: 594679 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1217128 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1090119 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1335902 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1260. Min Act: -0.0000

Data Index: 322791 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1359224 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1094. Min Act: -0.0000

Data Index: 771702 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.0750. Min Act: -0.0000

Data Index: 520114 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1173963 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.7322. Min Range: -1.7322

Max Act: 1.0490. Min Act: -0.0000

Data Index: 472642 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.7322. Min Range: -1.7322

Max Act: 0.9810. Min Act: -0.0000

Data Index: 339895 (C4 (Web Text))

Max Activating Token Index: 101