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

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

Neuron 1805 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1934. Min Act: -0.0000

Data Index: 1084720 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.9673. Min Act: -0.0000

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0484. Min Act: -0.0000

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.7460. Min Act: -0.0000

Data Index: 234407 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5908. Min Act: -0.0000

Data Index: 298540 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1240185 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5102. Min Act: -0.0000

Data Index: 749022 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.5023. Min Act: -0.0000

Data Index: 1133541 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.0873. Min Act: -0.0000

Data Index: 93580 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.2492. Min Act: -0.0000

Data Index: 606649 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.2468. Min Act: -0.0000

Data Index: 1296628 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.3662. Min Act: -0.0000

Data Index: 1194475 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.1060. Min Act: -0.0000

Data Index: 831955 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.1554. Min Act: -0.0000

Data Index: 199146 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.0194. Min Act: -0.0000

Data Index: 577721 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 3.1934. Min Range: -3.1934

Max Act: 1.9776. Min Act: -0.0000

Data Index: 511354 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 3.1934. Min Range: -3.1934

Max Act: 1.9996. Min Act: -0.0000

Data Index: 190795 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.1934. Min Range: -3.1934

Max Act: 1.9537. Min Act: -0.0000

Data Index: 126239 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.1934. Min Range: -3.1934

Max Act: 2.1791. Min Act: -0.0000

Data Index: 857577 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.1934. Min Range: -3.1934

Max Act: 1.9953. Min Act: -0.0000

Data Index: 11427 (C4 (Web Text))

Max Activating Token Index: 784