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

Dataset: The Pile

Neuron 2867 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1071188 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2760. Min Act: -0.0000

Data Index: 94448 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1577177 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2453. Min Act: -0.0000

Data Index: 79384 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1378816 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2387. Min Act: -0.0000

Data Index: 794592 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1372113 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2087. Min Act: -0.0000

Data Index: 992168 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2154. Min Act: -0.0000

Data Index: 145903 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1060499 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1395732 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1130042 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1569148 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1734990 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1987196 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1202994 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1935. Min Act: -0.0000

Data Index: 271588 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1718. Min Act: -0.0000

Data Index: 124062 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.1871. Min Act: -0.0000

Data Index: 432506 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.2963. Min Range: -0.2963

Max Act: 0.2063. Min Act: -0.0000

Data Index: 999821 (The Pile)

Max Activating Token Index: 209