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

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

Neuron 5206 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.8698. Min Act: -0.0000

Data Index: 599925 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.7459. Min Act: -0.0000

Data Index: 260240 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.6872. Min Act: -0.0000

Data Index: 1127369 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.5713. Min Act: -0.0000

Data Index: 438532 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.5289. Min Act: -0.0000

Data Index: 573974 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.4828. Min Act: -0.0000

Data Index: 954092 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3627. Min Act: -0.0000

Data Index: 281164 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.4416. Min Act: -0.0000

Data Index: 113004 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.4040. Min Act: -0.0000

Data Index: 665928 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3851. Min Act: -0.0000

Data Index: 501448 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3560. Min Act: -0.0000

Data Index: 1055775 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3434. Min Act: -0.0000

Data Index: 21321 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1409357 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1102928 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3218. Min Act: -0.0000

Data Index: 895631 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1303762 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1204378 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.2249. Min Act: -0.0000

Data Index: 157679 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1340153 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.8698. Min Range: -1.8698

Max Act: 1.2840. Min Act: -0.0000

Data Index: 307708 (C4 (Web Text))

Max Activating Token Index: 350