Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3549. Min Act: -0.0001

Data Index: 789325 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3032. Min Act: -0.0001

Data Index: 424476 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2654. Min Act: -0.0001

Data Index: 101813 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2746. Min Act: -0.0001

Data Index: 948918 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2634. Min Act: -0.0001

Data Index: 1029125 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2579. Min Act: -0.0001

Data Index: 279250 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2521. Min Act: -0.0001

Data Index: 36187 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2675. Min Act: -0.0001

Data Index: 747881 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2567. Min Act: -0.0001

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2452. Min Act: -0.0001

Data Index: 350021 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2541. Min Act: -0.0001

Data Index: 1173083 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2601. Min Act: -0.0001

Data Index: 271849 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2414. Min Act: -0.0001

Data Index: 172073 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2484. Min Act: -0.0001

Data Index: 1042143 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2405. Min Act: -0.0001

Data Index: 789885 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1048965 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2367. Min Act: -0.0001

Data Index: 400130 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2344. Min Act: -0.0001

Data Index: 701998 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1306683 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2323. Min Act: -0.0001

Data Index: 629506 (C4 (Web Text))

Max Activating Token Index: 119