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

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

Neuron 3652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8925. Min Range: -2.8925

Max Act: 2.8925. Min Act: -0.0000

Data Index: 140601 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.8925. Min Range: -2.8925

Max Act: 2.4601. Min Act: -0.0000

Data Index: 90244 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 2.8925. Min Range: -2.8925

Max Act: 2.1093. Min Act: -0.0000

Data Index: 41507 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 2.8925. Min Range: -2.8925

Max Act: 2.0920. Min Act: -0.0000

Data Index: 933897 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 2.8925. Min Range: -2.8925

Max Act: 2.0788. Min Act: -0.0000

Data Index: 954603 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.8662. Min Act: -0.0000

Data Index: 906628 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1098158 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5728. Min Act: -0.0000

Data Index: 666950 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5202. Min Act: -0.0000

Data Index: 416327 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5635. Min Act: -0.0000

Data Index: 800534 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5667. Min Act: -0.0000

Data Index: 413477 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5271. Min Act: -0.0000

Data Index: 56644 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1042956 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.5086. Min Act: -0.0000

Data Index: 540175 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.4251. Min Act: -0.0000

Data Index: 481074 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.4863. Min Act: -0.0000

Data Index: 837551 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.4834. Min Act: -0.0000

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.3907. Min Act: -0.0000

Data Index: 575647 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.4465. Min Act: -0.0000

Data Index: 1089496 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 2.8925. Min Range: -2.8925

Max Act: 1.4217. Min Act: -0.0000

Data Index: 15724 (C4 (Web Text))

Max Activating Token Index: 421