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

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

Neuron 400 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1064574 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.3037. Min Act: -0.0000

Data Index: 746352 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1228383 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1107670 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2818. Min Act: -0.0000

Data Index: 14192 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2827. Min Act: -0.0000

Data Index: 530692 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1204984 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1221119 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2526. Min Act: -0.0000

Data Index: 634677 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1346262 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2742. Min Act: -0.0000

Data Index: 694031 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2653. Min Act: -0.0000

Data Index: 516680 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2505. Min Act: -0.0000

Data Index: 266566 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1175067 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2658. Min Act: -0.0000

Data Index: 3162 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1313744 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2635. Min Act: -0.0000

Data Index: 925036 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2601. Min Act: -0.0000

Data Index: 798617 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2499. Min Act: -0.0000

Data Index: 274894 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2674. Min Act: -0.0000

Data Index: 38131 (C4 (Web Text))

Max Activating Token Index: 59