Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2543 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9524. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7800. Min Act: -0.0001

Data Index: 322245 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.6873. Min Act: -0.0001

Data Index: 689172 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7290. Min Act: -0.0001

Data Index: 1217578 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7041. Min Act: -0.0001

Data Index: 520814 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.6111. Min Act: -0.0001

Data Index: 1086623 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5943. Min Act: -0.0001

Data Index: 536684 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5678. Min Act: -0.0001

Data Index: 1092912 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.6014. Min Act: -0.0001

Data Index: 170718 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5606. Min Act: -0.0001

Data Index: 701027 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5774. Min Act: -0.0001

Data Index: 221374 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5519. Min Act: -0.0001

Data Index: 1222533 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1186373 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5472. Min Act: -0.0001

Data Index: 1044145 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5259. Min Act: -0.0001

Data Index: 916497 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5210. Min Act: -0.0001

Data Index: 766236 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1377988 (Python Code)

Max Activating Token Index: 156

Text #19

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.5141. Min Act: -0.0001

Data Index: 236897 (C4 (Web Text))

Max Activating Token Index: 152