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

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

Neuron 5851 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.8973. Min Act: -0.0000

Data Index: 1345263 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.7412. Min Act: -0.0000

Data Index: 413031 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.3163. Min Act: -0.0000

Data Index: 747046 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1212959 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2906. Min Act: -0.0000

Data Index: 565431 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1071486 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2430. Min Act: -0.0000

Data Index: 723347 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2462. Min Act: -0.0000

Data Index: 31431 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1138 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.2200. Min Act: -0.0000

Data Index: 46621 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1773. Min Act: -0.0000

Data Index: 835277 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1586. Min Act: -0.0000

Data Index: 654121 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1516. Min Act: -0.0000

Data Index: 895050 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1665. Min Act: -0.0000

Data Index: 503045 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1034007 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1276642 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1246163 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.0479. Min Act: -0.0000

Data Index: 122459 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.1044. Min Act: -0.0000

Data Index: 668661 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.8973. Min Range: -1.8973

Max Act: 1.0378. Min Act: -0.0000

Data Index: 382630 (C4 (Web Text))

Max Activating Token Index: 225