Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 201 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.3948. Min Act: 0.0000

Data Index: 1256297 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.2774. Min Act: -0.0000

Data Index: 305757 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1213217 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.2097. Min Act: -0.0000

Data Index: 771897 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.2109. Min Act: -0.0000

Data Index: 88326 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.2816. Min Act: -0.0000

Data Index: 280640 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1949. Min Act: -0.0000

Data Index: 115556 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1954. Min Act: -0.0000

Data Index: 330597 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1781. Min Act: -0.0001

Data Index: 334643 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.0968. Min Act: -0.0000

Data Index: 405634 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1426. Min Act: -0.0000

Data Index: 774002 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1108633 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1260. Min Act: -0.0000

Data Index: 896626 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1111. Min Act: -0.0000

Data Index: 255752 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1341891 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.0973. Min Act: -0.0000

Data Index: 9415 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1275. Min Act: -0.0000

Data Index: 223506 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.1263. Min Act: -0.0001

Data Index: 1251671 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.0602. Min Act: -0.0001

Data Index: 982410 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 1.3948. Min Range: -1.3948

Max Act: 1.0830. Min Act: -0.0000

Data Index: 378872 (C4 (Web Text))

Max Activating Token Index: 181