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

Dataset: The Pile

Neuron 579 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: 1.0680. Min Range: -1.0680

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1022311 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 1.0680. Min Range: -1.0680

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1019525 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9962. Min Act: -0.0000

Data Index: 468906 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 1.0680. Min Range: -1.0680

Max Act: 1.0316. Min Act: -0.0000

Data Index: 897666 (The Pile)

Max Activating Token Index: 864

Text #4

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1927133 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1693142 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8316. Min Act: -0.0000

Data Index: 46026 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1283235 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8540. Min Act: -0.0000

Data Index: 816514 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1657488 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1840187 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7912. Min Act: -0.0000

Data Index: 464101 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8499. Min Act: -0.0000

Data Index: 749803 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1455584 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1345223 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8281. Min Act: -0.0000

Data Index: 676107 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8056. Min Act: -0.0000

Data Index: 338002 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1341923 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7879. Min Act: -0.0000

Data Index: 623060 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1111937 (The Pile)

Max Activating Token Index: 929