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

Dataset: The Pile

Neuron 4438 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.8089. Min Act: -0.0000

Data Index: 451539 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1881020 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1393301 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.4725. Min Act: -0.0000

Data Index: 351903 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1954989 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.3744. Min Act: -0.0000

Data Index: 349883 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1093089 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1458381 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.3316. Min Act: -0.0000

Data Index: 221783 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1592505 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1114557 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.4375. Min Act: -0.0000

Data Index: 32317 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.3163. Min Act: -0.0000

Data Index: 799883 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.1607. Min Act: -0.0000

Data Index: 847849 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.2657. Min Act: -0.0000

Data Index: 928533 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.1820. Min Act: -0.0000

Data Index: 731374 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1173337 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1368518 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1340083 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1849920 (The Pile)

Max Activating Token Index: 399