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

Dataset: The Pile

Neuron 3451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.6939. Min Act: -0.0000

Data Index: 582794 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5973. Min Act: -0.0000

Data Index: 376770 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1038320 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5486. Min Act: -0.0000

Data Index: 201323 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4937. Min Act: -0.0000

Data Index: 533898 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4964. Min Act: -0.0000

Data Index: 740597 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5278. Min Act: -0.0000

Data Index: 11991 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4863. Min Act: -0.0000

Data Index: 124901 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4861. Min Act: -0.0000

Data Index: 814871 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4749. Min Act: -0.0000

Data Index: 402280 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1712746 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1842628 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1179187 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1211314 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4336. Min Act: -0.0000

Data Index: 673087 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1891058 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1709032 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1200861 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1947633 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 0.6939. Min Range: -0.6939

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1789261 (The Pile)

Max Activating Token Index: 339