Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 661 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.3026. Min Act: -0.0000

Data Index: 470385 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.1478. Min Act: -0.0000

Data Index: 221237 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1187339 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.0611. Min Act: -0.0000

Data Index: 485387 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.0062. Min Act: -0.0000

Data Index: 903902 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.2190. Min Act: -0.0000

Data Index: 903471 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8545. Min Act: -0.0000

Data Index: 366455 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.9385. Min Act: -0.0000

Data Index: 967878 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.9339. Min Act: -0.0000

Data Index: 179471 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.9140. Min Act: -0.0000

Data Index: 341601 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8045. Min Act: -0.0000

Data Index: 889455 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8128. Min Act: -0.0000

Data Index: 940800 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8025. Min Act: -0.0000

Data Index: 474176 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.6250. Min Act: -0.0000

Data Index: 383406 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8800. Min Act: -0.0000

Data Index: 40937 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.7619. Min Act: -0.0000

Data Index: 147737 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.7234. Min Act: -0.0000

Data Index: 802231 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1047736 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.6983. Min Act: -0.0000

Data Index: 348493 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.7951. Min Act: -0.0000

Data Index: 1056057 (C4 (Web Text))

Max Activating Token Index: 794