Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 826 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6591. Min Act: -0.0003

Data Index: 1107578 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6754. Min Act: -0.0003

Data Index: 1286234 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6196. Min Act: -0.0003

Data Index: 742378 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6401. Min Act: -0.0003

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5971. Min Act: -0.0003

Data Index: 121356 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6070. Min Act: -0.0003

Data Index: 622150 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6361. Min Act: -0.0003

Data Index: 237140 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.6258. Min Act: -0.0003

Data Index: 44987 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5419. Min Act: -0.0003

Data Index: 550568 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5966. Min Act: -0.0003

Data Index: 1196523 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5483. Min Act: -0.0003

Data Index: 776704 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.4690. Min Act: -0.0003

Data Index: 208860 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5467. Min Act: -0.0003

Data Index: 931098 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5257. Min Act: -0.0003

Data Index: 148540 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5750. Min Act: -0.0003

Data Index: 62986 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5646. Min Act: -0.0003

Data Index: 974501 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5520. Min Act: -0.0003

Data Index: 419774 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5358. Min Act: -0.0003

Data Index: 533965 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.4833. Min Act: -0.0003

Data Index: 735976 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.6754. Min Range: -0.6754

Max Act: 0.5381. Min Act: -0.0003

Data Index: 1346228 (C4 (Web Text))

Max Activating Token Index: 599