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

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

Neuron 1500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1267159 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8795. Min Act: -0.0000

Data Index: 2173 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1328914 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8055. Min Act: -0.0000

Data Index: 217050 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8667. Min Act: -0.0000

Data Index: 27101 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7782. Min Act: -0.0000

Data Index: 894799 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7991. Min Act: -0.0000

Data Index: 186319 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8191. Min Act: -0.0000

Data Index: 288215 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7890. Min Act: -0.0000

Data Index: 910081 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7789. Min Act: -0.0000

Data Index: 638853 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7571. Min Act: -0.0000

Data Index: 538655 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7631. Min Act: -0.0000

Data Index: 741932 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7545. Min Act: -0.0000

Data Index: 342001 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7424. Min Act: -0.0000

Data Index: 415121 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7601. Min Act: 0.0000

Data Index: 536531 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1314555 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7692. Min Act: -0.0000

Data Index: 215858 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1316727 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7627. Min Act: -0.0000

Data Index: 361857 (C4 (Web Text))

Max Activating Token Index: 148