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

Dataset: The Pile

Neuron 685 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1443687 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.2790. Min Act: -0.0000

Data Index: 26992 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3546. Min Act: -0.0000

Data Index: 895688 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1517855 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3698. Min Act: -0.0000

Data Index: 412833 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1862222 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4122. Min Act: -0.0000

Data Index: 552552 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4153. Min Act: -0.0000

Data Index: 110029 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1259556 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1259479 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3535. Min Act: -0.0000

Data Index: 654269 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1764454 (The Pile)

Max Activating Token Index: 909

Text #12

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1207109 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1764845 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3343. Min Act: -0.0000

Data Index: 513653 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1059224 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.2990. Min Act: -0.0000

Data Index: 725560 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1250125 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3111. Min Act: -0.0000

Data Index: 575346 (The Pile)

Max Activating Token Index: 447

Text #19

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.2911. Min Act: -0.0000

Data Index: 253387 (The Pile)

Max Activating Token Index: 1023