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

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

Neuron 4541 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.6754. Min Act: -0.0000

Data Index: 525808 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.5948. Min Act: -0.0000

Data Index: 746178 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.6862. Min Act: -0.0000

Data Index: 411329 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.6218. Min Act: -0.0000

Data Index: 782225 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.3015. Min Act: -0.0000

Data Index: 587203 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.2738. Min Act: -0.0000

Data Index: 766020 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.2212. Min Act: -0.0000

Data Index: 840961 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.2008. Min Act: -0.0000

Data Index: 180438 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1853. Min Act: 0.0000

Data Index: 1135174 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1763. Min Act: -0.0000

Data Index: 106552 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1348054 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1769. Min Act: -0.0000

Data Index: 59147 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.0762. Min Act: -0.0000

Data Index: 370437 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.0707. Min Act: 0.0000

Data Index: 1093013 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1306. Min Act: -0.0000

Data Index: 414074 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1316. Min Act: 0.0000

Data Index: 1100216 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1516. Min Act: -0.0000

Data Index: 749395 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1110037 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1023477 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.6862. Min Range: -1.6862

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1045925 (C4 (Web Text))

Max Activating Token Index: 718