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

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

Neuron 579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.2098. Min Act: -0.0000

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.1667. Min Act: -0.0000

Data Index: 246946 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.1428. Min Act: -0.0000

Data Index: 709011 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9685. Min Act: -0.0000

Data Index: 576895 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.2098. Min Range: -1.2098

Max Act: 1.0159. Min Act: -0.0000

Data Index: 87358 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9301. Min Act: -0.0000

Data Index: 910388 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8841. Min Act: -0.0000

Data Index: 410208 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8207. Min Act: -0.0000

Data Index: 934272 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9292. Min Act: -0.0000

Data Index: 307297 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8810. Min Act: -0.0000

Data Index: 435113 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9078. Min Act: -0.0000

Data Index: 6530 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8842. Min Act: -0.0000

Data Index: 263827 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1244425 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1258080 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8849. Min Act: -0.0000

Data Index: 674074 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8143. Min Act: -0.0000

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1042900 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1020968 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.8834. Min Act: -0.0000

Data Index: 849454 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.2098. Min Range: -1.2098

Max Act: 0.7829. Min Act: -0.0000

Data Index: 104342 (C4 (Web Text))

Max Activating Token Index: 693