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

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

Neuron 4696 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.8247. Min Act: -0.0000

Data Index: 274122 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7655. Min Act: -0.0000

Data Index: 262659 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.8037. Min Act: -0.0000

Data Index: 296805 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7625. Min Act: -0.0000

Data Index: 512508 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1131410 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1245869 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7375. Min Act: -0.0000

Data Index: 612868 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1197060 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7125. Min Act: -0.0000

Data Index: 50703 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.7365. Min Act: -0.0000

Data Index: 467322 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1150092 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6575. Min Act: -0.0000

Data Index: 591025 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1350457 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6779. Min Act: -0.0000

Data Index: 876528 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6590. Min Act: -0.0000

Data Index: 934121 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6607. Min Act: 0.0001

Data Index: 133650 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1345057 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1349906 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6125. Min Act: -0.0000

Data Index: 177969 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.8247. Min Range: -0.8247

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1238636 (C4 (Web Text))

Max Activating Token Index: 56