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

Dataset: The Pile

Neuron 3000 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: 0.7048. Min Range: -0.7048

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1987269 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1159316 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5649. Min Act: -0.0000

Data Index: 628578 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5520. Min Act: -0.0000

Data Index: 507719 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1202177 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5518. Min Act: -0.0000

Data Index: 932834 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5274. Min Act: -0.0000

Data Index: 845889 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1352277 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1107336 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5297. Min Act: -0.0000

Data Index: 911041 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5135. Min Act: -0.0000

Data Index: 460531 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4903. Min Act: -0.0000

Data Index: 285789 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1978885 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5064. Min Act: -0.0000

Data Index: 194095 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4746. Min Act: -0.0000

Data Index: 656023 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5139. Min Act: -0.0000

Data Index: 337671 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4886. Min Act: -0.0000

Data Index: 133721 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4713. Min Act: -0.0000

Data Index: 492969 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4796. Min Act: -0.0000

Data Index: 836828 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4827. Min Act: -0.0000

Data Index: 762623 (The Pile)

Max Activating Token Index: 343