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

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

Neuron 4138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.8085. Min Act: -0.0000

Data Index: 822803 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1070193 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7501. Min Act: -0.0000

Data Index: 237133 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1193241 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7257. Min Act: -0.0000

Data Index: 632032 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1120374 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6973. Min Act: -0.0000

Data Index: 561836 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6900. Min Act: -0.0000

Data Index: 174145 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7086. Min Act: -0.0000

Data Index: 884749 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6888. Min Act: -0.0000

Data Index: 895371 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6415. Min Act: -0.0000

Data Index: 218076 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6233. Min Act: -0.0000

Data Index: 868681 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6047. Min Act: -0.0000

Data Index: 213713 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1028210 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5290. Min Act: -0.0000

Data Index: 671568 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5970. Min Act: -0.0000

Data Index: 876745 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6029. Min Act: -0.0000

Data Index: 193408 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5303. Min Act: -0.0000

Data Index: 72077 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5773. Min Act: -0.0000

Data Index: 428031 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.5779. Min Act: -0.0000

Data Index: 844860 (C4 (Web Text))

Max Activating Token Index: 405