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

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

Neuron 4357 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0001

Data Index: 163912 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0696. Min Act: -0.0001

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1060067 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1335810 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0592. Min Act: -0.0001

Data Index: 52558 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1144829 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1010738 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1293449 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0535. Min Act: -0.0001

Data Index: 122607 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1281850 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1129686 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1322621 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0523. Min Act: -0.0001

Data Index: 150481 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0519. Min Act: -0.0001

Data Index: 423141 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0522. Min Act: -0.0001

Data Index: 197976 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0521. Min Act: -0.0001

Data Index: 145946 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1286861 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1167242 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1111608 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0498. Min Act: -0.0001

Data Index: 39677 (C4 (Web Text))

Max Activating Token Index: 4