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

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

Neuron 4273 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: 2.9478. Min Range: -2.9478

Max Act: 2.9478. Min Act: -0.0000

Data Index: 1340631 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.9384. Min Act: -0.0000

Data Index: 164715 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.4425. Min Act: -0.0000

Data Index: 1040429 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.5090. Min Act: -0.0000

Data Index: 701805 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.5185. Min Act: -0.0000

Data Index: 597029 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.5134. Min Act: -0.0000

Data Index: 366154 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.5056. Min Act: -0.0001

Data Index: 24816 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 2.9478. Min Range: -2.9478

Max Act: 1.9054. Min Act: -0.0000

Data Index: 382817 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.5987. Min Act: -0.0000

Data Index: 41853 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.3022. Min Act: -0.0000

Data Index: 726622 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.3378. Min Act: -0.0000

Data Index: 835356 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.3155. Min Act: -0.0000

Data Index: 333806 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.2675. Min Act: -0.0000

Data Index: 1035994 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.2785. Min Act: -0.0000

Data Index: 155765 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.1573. Min Act: -0.0001

Data Index: 187955 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.1681. Min Act: -0.0000

Data Index: 853635 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.1535. Min Act: -0.0000

Data Index: 1530 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.0378. Min Act: -0.0000

Data Index: 199654 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.5959. Min Act: -0.0001

Data Index: 1121205 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 2.9478. Min Range: -2.9478

Max Act: 2.3433. Min Act: -0.0000

Data Index: 40997 (C4 (Web Text))

Max Activating Token Index: 83