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

Dataset: The Pile

Neuron 3043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.0400. Min Range: -5.0400

Max Act: 5.0400. Min Act: -0.0000

Data Index: 769526 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.6117. Min Act: -0.0000

Data Index: 1439269 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.4221. Min Act: -0.0000

Data Index: 1994701 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.1985. Min Act: -0.0000

Data Index: 1789074 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.1579. Min Act: -0.0000

Data Index: 59464 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.9692. Min Act: -0.0000

Data Index: 1344771 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.2716. Min Act: -0.0000

Data Index: 1262868 (The Pile)

Max Activating Token Index: 658

Text #7

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.9699. Min Act: -0.0000

Data Index: 165767 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.9713. Min Act: -0.0000

Data Index: 434184 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.9445. Min Act: -0.0000

Data Index: 1919104 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.4305. Min Act: -0.0000

Data Index: 696582 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.6098. Min Act: -0.0000

Data Index: 557516 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.8802. Min Act: -0.0000

Data Index: 518559 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.2161. Min Act: -0.0000

Data Index: 815544 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.1820. Min Act: -0.0000

Data Index: 155677 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.8368. Min Act: -0.0000

Data Index: 1338363 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 5.0400. Min Range: -5.0400

Max Act: 4.0061. Min Act: -0.0000

Data Index: 941658 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.8062. Min Act: -0.0000

Data Index: 1250626 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.9573. Min Act: -0.0000

Data Index: 521514 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 5.0400. Min Range: -5.0400

Max Act: 3.9580. Min Act: -0.0000

Data Index: 415280 (The Pile)

Max Activating Token Index: 479