Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1198620 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3378. Min Act: -0.0000

Data Index: 369809 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3474. Min Act: -0.0000

Data Index: 858486 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1341868 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3217. Min Act: -0.0001

Data Index: 678630 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1122581 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1308304 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3112. Min Act: -0.0001

Data Index: 992880 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3360. Min Act: -0.0000

Data Index: 361350 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1050504 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2984. Min Act: -0.0000

Data Index: 682466 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2844. Min Act: -0.0000

Data Index: 495516 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1322535 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2823. Min Act: -0.0000

Data Index: 226352 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1241465 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3004. Min Act: -0.0000

Data Index: 757417 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2904. Min Act: -0.0000

Data Index: 934076 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2879. Min Act: -0.0000

Data Index: 132780 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.3084. Min Act: -0.0001

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.4151. Min Range: -0.4151

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 177