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

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

Neuron 2139 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: 1.4667. Min Range: -1.4667

Max Act: 1.4667. Min Act: -0.0000

Data Index: 366088 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3539. Min Act: -0.0000

Data Index: 681877 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1105894 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1203468 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2343. Min Act: -0.0000

Data Index: 975907 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1810. Min Act: -0.0000

Data Index: 406794 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1808. Min Act: -0.0000

Data Index: 730707 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1060405 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1978. Min Act: -0.0000

Data Index: 108215 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1056259 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3011. Min Act: -0.0000

Data Index: 431587 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0728. Min Act: -0.0000

Data Index: 722374 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0894. Min Act: -0.0000

Data Index: 77745 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1325572 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.1099. Min Act: -0.0000

Data Index: 237234 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1021971 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0952. Min Act: -0.0000

Data Index: 958309 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1155233 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1070568 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1352680 (C4 (Web Text))

Max Activating Token Index: 63