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

Dataset: The Pile

Neuron 1824 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: 0.7183. Min Range: -0.7183

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1996012 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6768. Min Act: -0.0000

Data Index: 565949 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6625. Min Act: -0.0000

Data Index: 880257 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1701574 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6269. Min Act: -0.0000

Data Index: 372102 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6134. Min Act: -0.0000

Data Index: 544285 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.6087. Min Act: -0.0000

Data Index: 969219 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1462754 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5939. Min Act: -0.0000

Data Index: 339350 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5772. Min Act: -0.0000

Data Index: 919667 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1369332 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5592. Min Act: -0.0000

Data Index: 976502 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1137473 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1638786 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5842. Min Act: -0.0000

Data Index: 483442 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1054069 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5616. Min Act: -0.0000

Data Index: 490065 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1653928 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5187. Min Act: -0.0000

Data Index: 832841 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.7183. Min Range: -0.7183

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1627491 (The Pile)

Max Activating Token Index: 399