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

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

Neuron 4053 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.1560. Min Act: -0.0000

Data Index: 530885 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0804. Min Act: -0.0001

Data Index: 206113 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9966. Min Act: -0.0001

Data Index: 276420 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0877. Min Act: -0.0000

Data Index: 714252 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.1102. Min Act: -0.0000

Data Index: 975391 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0366. Min Act: -0.0000

Data Index: 465768 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0324. Min Act: -0.0001

Data Index: 1103019 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9934. Min Act: -0.0001

Data Index: 256509 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0085. Min Act: -0.0001

Data Index: 1168278 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9949. Min Act: -0.0000

Data Index: 832678 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1295919 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9912. Min Act: -0.0001

Data Index: 1236123 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9378. Min Act: -0.0001

Data Index: 392136 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9594. Min Act: -0.0001

Data Index: 487975 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9338. Min Act: -0.0000

Data Index: 519181 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9504. Min Act: -0.0001

Data Index: 236370 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8999. Min Act: -0.0001

Data Index: 1322316 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8995. Min Act: -0.0001

Data Index: 784234 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9298. Min Act: -0.0001

Data Index: 155550 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.9544. Min Act: -0.0001

Data Index: 151695 (C4 (Web Text))

Max Activating Token Index: 1022