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

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

Neuron 1440 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.6043. Min Act: -0.0000

Data Index: 651962 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1355188 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1038842 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1441089 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4326. Min Act: -0.0000

Data Index: 859350 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3551. Min Act: -0.0000

Data Index: 842914 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3039. Min Act: -0.0000

Data Index: 678085 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2712. Min Act: -0.0000

Data Index: 398870 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1151714 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2243. Min Act: -0.0000

Data Index: 667221 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1612582 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4252. Min Act: -0.0000

Data Index: 144529 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1597. Min Act: -0.0000

Data Index: 281598 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1591. Min Act: -0.0000

Data Index: 107771 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1082416 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1422. Min Act: -0.0000

Data Index: 832214 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1319. Min Act: -0.0000

Data Index: 694243 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2012. Min Act: -0.0000

Data Index: 573213 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1547. Min Act: -0.0000

Data Index: 406636 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1108. Min Act: -0.0000

Data Index: 402636 (C4 (Web Text))

Max Activating Token Index: 132