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

Dataset: The Pile

Neuron 2618 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.5010. Min Act: -0.0000

Data Index: 894739 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2256. Min Act: -0.0000

Data Index: 998472 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.1705. Min Act: -0.0000

Data Index: 1272140 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.0529. Min Act: -0.0000

Data Index: 1218989 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.0098. Min Act: -0.0000

Data Index: 1856688 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.0121. Min Act: -0.0000

Data Index: 527988 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.8879. Min Act: -0.0000

Data Index: 1487783 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.6627. Min Act: -0.0000

Data Index: 146422 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.5132. Min Act: -0.0000

Data Index: 203763 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.6351. Min Act: -0.0000

Data Index: 1151476 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.5267. Min Act: -0.0000

Data Index: 241349 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.3617. Min Act: -0.0000

Data Index: 145181 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.6003. Min Act: -0.0000

Data Index: 1844197 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.4392. Min Act: -0.0000

Data Index: 775047 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.3700. Min Act: -0.0000

Data Index: 237129 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.2667. Min Act: -0.0000

Data Index: 1548661 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.5046. Min Act: -0.0000

Data Index: 983173 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.9346. Min Act: -0.0000

Data Index: 1487698 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.2691. Min Act: -0.0000

Data Index: 426397 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.3934. Min Act: -0.0000

Data Index: 778271 (The Pile)

Max Activating Token Index: 213