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

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

Neuron 3663 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.4959. Min Act: -0.0000

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.4661. Min Act: -0.0000

Data Index: 358775 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.2574. Min Act: 0.0000

Data Index: 29836 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.0403. Min Act: -0.0000

Data Index: 955091 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.0932. Min Act: -0.0000

Data Index: 387750 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.1512. Min Act: -0.0000

Data Index: 619968 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.9359. Min Act: -0.0000

Data Index: 678506 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.9076. Min Act: -0.0000

Data Index: 601074 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.0058. Min Act: -0.0000

Data Index: 146522 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.9553. Min Act: -0.0000

Data Index: 491748 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.0393. Min Act: -0.0000

Data Index: 994648 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 2.4959. Min Range: -2.4959

Max Act: 2.0395. Min Act: -0.0000

Data Index: 851668 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.7902. Min Act: -0.0000

Data Index: 335275 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.9135. Min Act: -0.0000

Data Index: 170947 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.7899. Min Act: -0.0000

Data Index: 1216474 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.8632. Min Act: -0.0000

Data Index: 253185 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.7570. Min Act: -0.0000

Data Index: 115845 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.7595. Min Act: -0.0000

Data Index: 914854 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.8675. Min Act: -0.0000

Data Index: 48463 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 2.4959. Min Range: -2.4959

Max Act: 1.7404. Min Act: -0.0000

Data Index: 3137 (C4 (Web Text))

Max Activating Token Index: 515