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

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

Neuron 2890 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 327010 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7198. Min Act: 0.0000

Data Index: 249821 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7203. Min Act: -0.0000

Data Index: 343743 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6137. Min Act: 0.0000

Data Index: 237903 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5833. Min Act: 0.0001

Data Index: 688628 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5781. Min Act: 0.0000

Data Index: 268874 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1169515 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5710. Min Act: 0.0000

Data Index: 1201603 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5591. Min Act: 0.0001

Data Index: 923234 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5652. Min Act: -0.0000

Data Index: 210754 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5329. Min Act: -0.0000

Data Index: 31882 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5502. Min Act: -0.0000

Data Index: 666752 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5598. Min Act: -0.0000

Data Index: 686351 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5255. Min Act: -0.0000

Data Index: 2472 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5348. Min Act: 0.0001

Data Index: 112343 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1292515 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5152. Min Act: -0.0000

Data Index: 884824 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5301. Min Act: -0.0000

Data Index: 954810 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5465. Min Act: -0.0000

Data Index: 955995 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5400. Min Act: -0.0000

Data Index: 259390 (C4 (Web Text))

Max Activating Token Index: 391