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

Dataset: The Pile

Neuron 3194 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: 1.8376. Min Range: -1.8376

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1052292 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1183242 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7164. Min Act: -0.0000

Data Index: 1142351 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1412909 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7647. Min Act: -0.0000

Data Index: 71536 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1431455 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.8158. Min Act: -0.0000

Data Index: 610891 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7169. Min Act: -0.0000

Data Index: 854689 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1412180 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1205066 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1710831 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.7146. Min Act: -0.0000

Data Index: 848316 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6768. Min Act: -0.0000

Data Index: 1883796 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6575. Min Act: -0.0000

Data Index: 332904 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.5701. Min Act: -0.0000

Data Index: 1447485 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6741. Min Act: -0.0000

Data Index: 1043963 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1642355 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1718217 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1870890 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 1.8376. Min Range: -1.8376

Max Act: 1.5489. Min Act: -0.0000

Data Index: 1620289 (The Pile)

Max Activating Token Index: 512