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

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

Neuron 3098 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: 1.8984. Min Range: -1.8984

Max Act: 1.8984. Min Act: -0.0000

Data Index: 84928 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8041. Min Act: -0.0000

Data Index: 292102 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.6808. Min Act: -0.0000

Data Index: 1299859 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7571. Min Act: -0.0000

Data Index: 467101 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5978. Min Act: -0.0000

Data Index: 266816 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5845. Min Act: -0.0000

Data Index: 1347507 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.3782. Min Act: -0.0000

Data Index: 858148 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4587. Min Act: -0.0000

Data Index: 795796 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5157. Min Act: -0.0000

Data Index: 946880 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5156. Min Act: -0.0000

Data Index: 855599 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4203. Min Act: -0.0000

Data Index: 25457 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.3978. Min Act: -0.0000

Data Index: 408679 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.3975. Min Act: -0.0000

Data Index: 658523 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4770. Min Act: -0.0000

Data Index: 259960 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1215795 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1051992 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4292. Min Act: -0.0000

Data Index: 454611 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4272. Min Act: -0.0000

Data Index: 568467 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.5716. Min Act: -0.0000

Data Index: 197646 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.4084. Min Act: -0.0000

Data Index: 247111 (C4 (Web Text))

Max Activating Token Index: 316