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

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

Neuron 5605 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: 1.3567. Min Range: -1.3567

Max Act: 1.3567. Min Act: -0.0000

Data Index: 892879 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3043. Min Act: -0.0000

Data Index: 21518 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.1812. Min Act: -0.0000

Data Index: 816571 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1134239 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0635. Min Act: -0.0000

Data Index: 460784 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0213. Min Act: -0.0000

Data Index: 275621 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9869. Min Act: -0.0000

Data Index: 898239 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9660. Min Act: -0.0000

Data Index: 734659 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9538. Min Act: -0.0000

Data Index: 846120 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1201822 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9335. Min Act: -0.0000

Data Index: 229562 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1266069 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1343154 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9054. Min Act: -0.0000

Data Index: 816368 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.8991. Min Act: -0.0000

Data Index: 90819 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.8215. Min Act: -0.0000

Data Index: 259428 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.8264. Min Act: -0.0000

Data Index: 393025 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.9378. Min Act: -0.0000

Data Index: 160853 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1204722 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.3567. Min Range: -1.3567

Max Act: 0.8831. Min Act: -0.0000

Data Index: 733864 (C4 (Web Text))

Max Activating Token Index: 630