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

Dataset: The Pile

Neuron 2717 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: 5.9088. Min Range: -5.9088

Max Act: 5.9088. Min Act: -0.0000

Data Index: 461081 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 5.9088. Min Range: -5.9088

Max Act: 5.8102. Min Act: -0.0000

Data Index: 81558 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 5.9088. Min Range: -5.9088

Max Act: 5.1352. Min Act: -0.0000

Data Index: 146600 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.3408. Min Act: -0.0000

Data Index: 566746 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.4642. Min Act: -0.0000

Data Index: 1116121 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.0922. Min Act: -0.0000

Data Index: 1563157 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.2209. Min Act: -0.0000

Data Index: 1989185 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.1854. Min Act: -0.0000

Data Index: 1436933 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.9039. Min Act: -0.0000

Data Index: 648545 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.8581. Min Act: -0.0000

Data Index: 509353 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.2015. Min Act: -0.0000

Data Index: 1774007 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 5.9088. Min Range: -5.9088

Max Act: 4.1916. Min Act: -0.0000

Data Index: 1893666 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.8574. Min Act: -0.0000

Data Index: 208677 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.8412. Min Act: -0.0000

Data Index: 742172 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.9501. Min Act: -0.0000

Data Index: 338592 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.9304. Min Act: -0.0000

Data Index: 870591 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.9067. Min Act: -0.0000

Data Index: 647393 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.7571. Min Act: -0.0000

Data Index: 1240927 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.9052. Min Act: -0.0000

Data Index: 1365512 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 5.9088. Min Range: -5.9088

Max Act: 3.5310. Min Act: -0.0000

Data Index: 1573783 (The Pile)

Max Activating Token Index: 629