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

Dataset: The Pile

Neuron 3237 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: 0.3660. Min Range: -0.3660

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1189544 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3660. Min Act: -0.0000

Data Index: 89261 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3306. Min Act: -0.0000

Data Index: 213344 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3265. Min Act: -0.0000

Data Index: 51341 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1426659 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3116. Min Act: -0.0000

Data Index: 676234 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1161133 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3062. Min Act: -0.0000

Data Index: 252204 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3287. Min Act: -0.0000

Data Index: 129039 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2780. Min Act: -0.0000

Data Index: 186125 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2938. Min Act: -0.0000

Data Index: 87231 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1965735 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1747410 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1185506 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2680. Min Act: -0.0000

Data Index: 860056 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2833. Min Act: -0.0000

Data Index: 62707 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3037. Min Act: -0.0000

Data Index: 34241 (The Pile)

Max Activating Token Index: 140

Text #17

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1813310 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1994537 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1340161 (The Pile)

Max Activating Token Index: 28