Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1680578 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1629232 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4751. Min Act: -0.0000

Data Index: 348305 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1928206 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1447145 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4498. Min Act: 0.0000

Data Index: 916349 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1055608 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1339316 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1842867 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1493736 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4423. Min Act: -0.0000

Data Index: 938198 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1732754 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4469. Min Act: -0.0000

Data Index: 735974 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4097. Min Act: -0.0000

Data Index: 75116 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3930. Min Act: -0.0000

Data Index: 936437 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1425403 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1646821 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3780. Min Act: -0.0000

Data Index: 124507 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1991399 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4337. Min Act: -0.0000

Data Index: 649653 (The Pile)

Max Activating Token Index: 47