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

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

Neuron 1907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1036403 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1221211 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9001. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8865. Min Act: -0.0000

Data Index: 603916 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1334904 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9007. Min Act: -0.0000

Data Index: 355671 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8224. Min Act: -0.0000

Data Index: 565760 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1196036 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1145710 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7602. Min Act: -0.0000

Data Index: 861785 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7615. Min Act: -0.0000

Data Index: 3923 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1131529 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7666. Min Act: -0.0000

Data Index: 868171 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7467. Min Act: -0.0000

Data Index: 441174 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7280. Min Act: -0.0000

Data Index: 250258 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7172. Min Act: -0.0000

Data Index: 934523 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6730. Min Act: -0.0000

Data Index: 481530 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7774. Min Act: -0.0000

Data Index: 884259 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1337489 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7433. Min Act: -0.0000

Data Index: 900367 (C4 (Web Text))

Max Activating Token Index: 791