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

Dataset: The Pile

Neuron 5030 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: 1.2865. Min Range: -1.2865

Max Act: 1.2865. Min Act: -0.0000

Data Index: 205835 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.1008. Min Act: -0.0000

Data Index: 124008 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1079814 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0924. Min Act: -0.0000

Data Index: 439860 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9943. Min Act: -0.0000

Data Index: 148989 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0532. Min Act: -0.0000

Data Index: 94942 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9290. Min Act: -0.0000

Data Index: 562839 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1334076 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9824. Min Act: -0.0000

Data Index: 106040 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1919531 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1000847 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9648. Min Act: -0.0000

Data Index: 568879 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8347. Min Act: -0.0000

Data Index: 964638 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1893526 (The Pile)

Max Activating Token Index: 470

Text #14

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9008. Min Act: -0.0000

Data Index: 489311 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1007242 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7558. Min Act: -0.0000

Data Index: 381925 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1094135 (The Pile)

Max Activating Token Index: 952

Text #18

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1846418 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1369905 (The Pile)

Max Activating Token Index: 71