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

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

Neuron 1422 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: 4.4509. Min Range: -4.4509

Max Act: 4.4509. Min Act: -0.0001

Data Index: 414797 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 4.4509. Min Range: -4.4509

Max Act: 4.0971. Min Act: -0.0000

Data Index: 259752 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.8060. Min Act: -0.0000

Data Index: 466246 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.7239. Min Act: -0.0000

Data Index: 188312 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.2727. Min Act: -0.0000

Data Index: 1062296 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.2551. Min Act: -0.0000

Data Index: 769389 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.3549. Min Act: -0.0000

Data Index: 1304970 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.9401. Min Act: -0.0000

Data Index: 559990 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.0254. Min Act: -0.0000

Data Index: 789254 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.0625. Min Act: -0.0000

Data Index: 374011 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.9133. Min Act: -0.0000

Data Index: 914820 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.0318. Min Act: -0.0000

Data Index: 1120017 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 4.4509. Min Range: -4.4509

Max Act: 3.0792. Min Act: -0.0000

Data Index: 987538 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.7347. Min Act: -0.0000

Data Index: 842774 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.9849. Min Act: -0.0000

Data Index: 523508 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.8341. Min Act: -0.0000

Data Index: 401488 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.5305. Min Act: -0.0000

Data Index: 34416 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.7736. Min Act: -0.0000

Data Index: 41988 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.7832. Min Act: -0.0000

Data Index: 508625 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 4.4509. Min Range: -4.4509

Max Act: 2.5572. Min Act: -0.0000

Data Index: 30550 (C4 (Web Text))

Max Activating Token Index: 38