Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3915 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5496. Min Range: -3.5496

Max Act: 3.5496. Min Act: -0.0000

Data Index: 491877 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.5848. Min Act: -0.0001

Data Index: 126723 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.5868. Min Act: -0.0001

Data Index: 801096 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.5133. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.3608. Min Act: -0.0001

Data Index: 544906 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.4275. Min Act: -0.0000

Data Index: 793274 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.4169. Min Act: -0.0000

Data Index: 26649 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.3241. Min Act: -0.0000

Data Index: 1004849 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.3929. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.1381. Min Act: -0.0000

Data Index: 952903 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.2408. Min Act: -0.0000

Data Index: 307646 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.3525. Min Act: -0.0001

Data Index: 914814 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.3417. Min Act: -0.0000

Data Index: 393523 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.3315. Min Act: -0.0000

Data Index: 262125 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.1978. Min Act: -0.0000

Data Index: 1243254 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.2999. Min Act: -0.0000

Data Index: 996136 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.2551. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.1447. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.2650. Min Act: -0.0001

Data Index: 1006323 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 3.5496. Min Range: -3.5496

Max Act: 2.1426. Min Act: -0.0001

Data Index: 373558 (C4 (Web Text))

Max Activating Token Index: 769