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

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

Neuron 1435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.9513. Min Act: -0.0000

Data Index: 1101997 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.5624. Min Act: -0.0000

Data Index: 410287 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.3692. Min Act: -0.0000

Data Index: 845157 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.1780. Min Act: -0.0000

Data Index: 1232335 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.1308. Min Act: -0.0000

Data Index: 381072 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.3153. Min Act: -0.0000

Data Index: 262107 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 8.9513. Min Range: -8.9513

Max Act: 8.3577. Min Act: -0.0000

Data Index: 773875 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 8.9513. Min Range: -8.9513

Max Act: 5.7650. Min Act: -0.0000

Data Index: 519761 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 8.9513. Min Range: -8.9513

Max Act: 5.6244. Min Act: -0.0000

Data Index: 479700 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 8.9513. Min Range: -8.9513

Max Act: 5.4210. Min Act: -0.0000

Data Index: 1316507 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.9203. Min Act: -0.0000

Data Index: 1064054 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 8.9513. Min Range: -8.9513

Max Act: 5.1030. Min Act: -0.0000

Data Index: 648875 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.8671. Min Act: -0.0000

Data Index: 577928 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.8502. Min Act: -0.0000

Data Index: 781013 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.9122. Min Act: -0.0000

Data Index: 452943 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.6739. Min Act: -0.0000

Data Index: 676018 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.6460. Min Act: -0.0000

Data Index: 154299 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.3760. Min Act: -0.0000

Data Index: 1227647 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.4952. Min Act: -0.0000

Data Index: 303793 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 8.9513. Min Range: -8.9513

Max Act: 4.4770. Min Act: -0.0000

Data Index: 34136 (C4 (Web Text))

Max Activating Token Index: 991