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

Dataset: The Pile

Neuron 1670 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: 0.8229. Min Range: -0.8229

Max Act: 0.8229. Min Act: -0.0000

Data Index: 540805 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1667228 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.7245. Min Act: -0.0000

Data Index: 899967 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6395. Min Act: -0.0000

Data Index: 44214 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1968227 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6991. Min Act: -0.0000

Data Index: 341378 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6310. Min Act: -0.0000

Data Index: 495331 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1358727 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6142. Min Act: -0.0000

Data Index: 341733 (The Pile)

Max Activating Token Index: 996

Text #9

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6486. Min Act: -0.0000

Data Index: 76009 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1435677 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6310. Min Act: -0.0000

Data Index: 316950 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1332408 (The Pile)

Max Activating Token Index: 670

Text #13

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1697733 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1526018 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5424. Min Act: -0.0000

Data Index: 451727 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1228716 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1252771 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.4946. Min Act: -0.0000

Data Index: 286269 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.4769. Min Act: -0.0000

Data Index: 687072 (The Pile)

Max Activating Token Index: 536