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

Dataset: The Pile

Neuron 171 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1128502 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5873. Min Act: -0.0000

Data Index: 752004 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5775. Min Act: -0.0000

Data Index: 680998 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5911. Min Act: -0.0000

Data Index: 801211 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5861. Min Act: -0.0000

Data Index: 313342 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1112970 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5526. Min Act: -0.0000

Data Index: 121043 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1074201 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1149821 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1440166 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4441. Min Act: -0.0000

Data Index: 868670 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1689653 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1476468 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1448610 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4502. Min Act: -0.0000

Data Index: 902703 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1614460 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1601670 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1488799 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1405515 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.8625. Min Range: -0.8625

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1288631 (The Pile)

Max Activating Token Index: 533