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

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

Neuron 2782 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: 1.0007. Min Range: -1.0007

Max Act: 1.0007. Min Act: -0.0001

Data Index: 734453 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.9283. Min Act: -0.0001

Data Index: 368488 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8752. Min Act: -0.0000

Data Index: 550073 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8932. Min Act: -0.0000

Data Index: 121718 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8355. Min Act: -0.0001

Data Index: 651498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1266065 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8416. Min Act: -0.0000

Data Index: 927274 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7583. Min Act: -0.0000

Data Index: 105932 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7921. Min Act: -0.0000

Data Index: 725520 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8411. Min Act: -0.0001

Data Index: 952151 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7907. Min Act: -0.0000

Data Index: 116538 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7781. Min Act: -0.0001

Data Index: 8098 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7974. Min Act: -0.0001

Data Index: 698443 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7966. Min Act: -0.0001

Data Index: 430039 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1132233 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7104. Min Act: -0.0001

Data Index: 1082570 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7295. Min Act: -0.0000

Data Index: 471258 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7198. Min Act: -0.0000

Data Index: 69824 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1280629 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7335. Min Act: -0.0000

Data Index: 514222 (C4 (Web Text))

Max Activating Token Index: 944