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

Dataset: The Pile

Neuron 608 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: 1.2987. Min Range: -1.2987

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1503108 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1654523 (The Pile)

Max Activating Token Index: 378

Text #2

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9365. Min Act: -0.0000

Data Index: 481535 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8315. Min Act: -0.0000

Data Index: 879872 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9441. Min Act: -0.0000

Data Index: 129221 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9014. Min Act: -0.0000

Data Index: 172352 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1321981 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1638140 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9275. Min Act: -0.0001

Data Index: 922541 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7496. Min Act: -0.0000

Data Index: 184141 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1972822 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8914. Min Act: -0.0000

Data Index: 795381 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1626237 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1331556 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8729. Min Act: -0.0000

Data Index: 941134 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7351. Min Act: -0.0000

Data Index: 179788 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1621846 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1458937 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8997. Min Act: -0.0000

Data Index: 292698 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7826. Min Act: -0.0000

Data Index: 816104 (The Pile)

Max Activating Token Index: 157