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

Dataset: The Pile

Neuron 2020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.5431. Min Act: -0.0000

Data Index: 450843 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4860. Min Act: -0.0001

Data Index: 114785 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4800. Min Act: -0.0000

Data Index: 153434 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1226251 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4549. Min Act: -0.0000

Data Index: 987281 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4269. Min Act: -0.0000

Data Index: 17806 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1639650 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1066584 (The Pile)

Max Activating Token Index: 655

Text #8

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4058. Min Act: -0.0000

Data Index: 379979 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1414533 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1780444 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4254. Min Act: -0.0000

Data Index: 433403 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1205397 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3735. Min Act: -0.0000

Data Index: 142745 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1465715 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3864. Min Act: -0.0000

Data Index: 446231 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1967016 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1217983 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3719. Min Act: -0.0000

Data Index: 126387 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 0.5431. Min Range: -0.5431

Max Act: 0.3209. Min Act: -0.0000

Data Index: 581134 (The Pile)

Max Activating Token Index: 1001