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

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

Neuron 4147 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: 1.9695. Min Range: -1.9695

Max Act: 1.9695. Min Act: -0.0000

Data Index: 1275626 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8343. Min Act: -0.0000

Data Index: 264963 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1263414 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.7159. Min Act: -0.0000

Data Index: 987939 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4648. Min Act: -0.0000

Data Index: 549746 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5076. Min Act: -0.0000

Data Index: 734148 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.5774. Min Act: -0.0000

Data Index: 499418 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3524. Min Act: -0.0000

Data Index: 185845 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1356432 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.4724. Min Act: -0.0000

Data Index: 468073 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1163291 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3713. Min Act: -0.0000

Data Index: 627387 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3568. Min Act: -0.0000

Data Index: 424618 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1303543 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.2912. Min Act: -0.0000

Data Index: 926541 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3045. Min Act: -0.0000

Data Index: 274766 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.2722. Min Act: -0.0000

Data Index: 903816 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.2587. Min Act: -0.0000

Data Index: 607635 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.2483. Min Act: -0.0000

Data Index: 503987 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.9695. Min Range: -1.9695

Max Act: 1.3213. Min Act: -0.0000

Data Index: 167137 (C4 (Web Text))

Max Activating Token Index: 694