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

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

Neuron 2077 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 484085 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1310. Min Act: -0.0001

Data Index: 434795 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1255. Min Act: -0.0001

Data Index: 391358 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1283. Min Act: -0.0001

Data Index: 526136 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1233. Min Act: -0.0001

Data Index: 29566 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1139. Min Act: -0.0001

Data Index: 713383 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1088. Min Act: -0.0000

Data Index: 916447 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1129. Min Act: -0.0001

Data Index: 383051 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1106. Min Act: -0.0001

Data Index: 256491 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1198181 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1052. Min Act: -0.0001

Data Index: 910786 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1087. Min Act: -0.0001

Data Index: 725767 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0975. Min Act: -0.0001

Data Index: 725259 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1048. Min Act: -0.0001

Data Index: 912134 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1092559 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1029. Min Act: -0.0001

Data Index: 42540 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1071. Min Act: -0.0001

Data Index: 390730 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1075. Min Act: -0.0001

Data Index: 954041 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1029. Min Act: -0.0001

Data Index: 866129 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1066. Min Act: -0.0001

Data Index: 965516 (C4 (Web Text))

Max Activating Token Index: 135