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

Dataset: The Pile

Neuron 905 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: 0.7025. Min Range: -0.7025

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1024319 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.6356. Min Act: -0.0000

Data Index: 517765 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1715219 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1354266 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5175. Min Act: -0.0000

Data Index: 484208 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1253141 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1671858 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5349. Min Act: -0.0000

Data Index: 585963 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1724762 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1139188 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5205. Min Act: -0.0000

Data Index: 258832 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5256. Min Act: -0.0000

Data Index: 901752 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4989. Min Act: -0.0000

Data Index: 203365 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1642708 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4666. Min Act: -0.0000

Data Index: 23279 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1494661 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1005833 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1224770 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1119620 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.7025. Min Range: -0.7025

Max Act: 0.4767. Min Act: -0.0000

Data Index: 589587 (The Pile)

Max Activating Token Index: 930