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

Dataset: The Pile

Neuron 1181 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: 0.8576. Min Range: -0.8576

Max Act: 0.8576. Min Act: -0.0000

Data Index: 353906 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.6397. Min Act: -0.0000

Data Index: 161510 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1063783 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5597. Min Act: -0.0000

Data Index: 17352 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5009. Min Act: -0.0000

Data Index: 679017 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5064. Min Act: -0.0000

Data Index: 731482 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1673004 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4809. Min Act: -0.0000

Data Index: 55769 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1731570 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3924. Min Act: -0.0000

Data Index: 634230 (The Pile)

Max Activating Token Index: 664

Text #10

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1646053 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1978316 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4267. Min Act: -0.0000

Data Index: 148357 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1118316 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3998. Min Act: -0.0000

Data Index: 11743 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3969. Min Act: -0.0000

Data Index: 224561 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3750. Min Act: -0.0000

Data Index: 803784 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1967108 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4154. Min Act: -0.0000

Data Index: 167163 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.3333. Min Act: -0.0000

Data Index: 148830 (The Pile)

Max Activating Token Index: 618