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

Dataset: The Pile

Neuron 482 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: 0.7393. Min Range: -0.7393

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1898579 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.7162. Min Act: -0.0000

Data Index: 496614 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6919. Min Act: -0.0000

Data Index: 170687 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1586054 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1905681 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6858. Min Act: -0.0000

Data Index: 856575 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1390159 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6497. Min Act: -0.0000

Data Index: 222743 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1062987 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6435. Min Act: -0.0000

Data Index: 442556 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1944251 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1001673 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1337864 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6275. Min Act: -0.0000

Data Index: 947512 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1996031 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6216. Min Act: -0.0000

Data Index: 820656 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6314. Min Act: -0.0000

Data Index: 158139 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1675538 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1864336 (The Pile)

Max Activating Token Index: 919

Text #19

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1559417 (The Pile)

Max Activating Token Index: 331