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

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

Neuron 2633 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.9754. Min Act: -0.0000

Data Index: 1603001 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1501726 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1555546 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1492661 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.6165. Min Act: -0.0000

Data Index: 1499066 (Python Code)

Max Activating Token Index: 1017

Text #5

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.6323. Min Act: -0.0000

Data Index: 1582091 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1371707 (Python Code)

Max Activating Token Index: 925

Text #7

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1494006 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1454142 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1618701 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1499001 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1554621 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4834. Min Act: -0.0000

Data Index: 1586790 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1656644 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1641247 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4271. Min Act: -0.0000

Data Index: 1385349 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1366731 (Python Code)

Max Activating Token Index: 997

Text #17

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3953. Min Act: -0.0000

Data Index: 1576549 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1646482 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1633012 (Python Code)

Max Activating Token Index: 66