Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2993 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.4217. Min Range: -4.4217

Max Act: 4.4217. Min Act: -0.0000

Data Index: 1903957 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 4.4217. Min Range: -4.4217

Max Act: 4.1885. Min Act: -0.0000

Data Index: 359192 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.8198. Min Act: -0.0000

Data Index: 1253756 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.9139. Min Act: -0.0000

Data Index: 76437 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.9268. Min Act: -0.0000

Data Index: 1149900 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.7796. Min Act: -0.0000

Data Index: 1423551 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.5593. Min Act: -0.0000

Data Index: 102468 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.6632. Min Act: -0.0000

Data Index: 957698 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.5286. Min Act: -0.0000

Data Index: 1482366 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.4933. Min Act: -0.0000

Data Index: 1499066 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.7423. Min Act: -0.0000

Data Index: 1096031 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.2067. Min Act: -0.0000

Data Index: 1689052 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.3180. Min Act: -0.0000

Data Index: 1907342 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.4284. Min Act: -0.0000

Data Index: 1363866 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.3515. Min Act: -0.0000

Data Index: 1515561 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.0786. Min Act: -0.0000

Data Index: 1666773 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.3121. Min Act: -0.0000

Data Index: 1486288 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.3837. Min Act: -0.0000

Data Index: 1865769 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 4.4217. Min Range: -4.4217

Max Act: 2.3765. Min Act: -0.0000

Data Index: 1701123 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 4.4217. Min Range: -4.4217

Max Act: 1.9927. Min Act: -0.0000

Data Index: 424044 (The Pile)

Max Activating Token Index: 849