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

Dataset: The Pile

Neuron 341 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: 0.4580. Min Range: -0.4580

Max Act: 0.4580. Min Act: -0.0000

Data Index: 11600 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1182658 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1618448 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1367240 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1700049 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1232195 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1196814 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1176664 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1719533 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1740435 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1101978 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1549102 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4016. Min Act: -0.0000

Data Index: 892209 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3648. Min Act: -0.0000

Data Index: 160798 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3503. Min Act: -0.0000

Data Index: 518281 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3376. Min Act: -0.0000

Data Index: 905706 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1445682 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1894966 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1129824 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3293. Min Act: -0.0000

Data Index: 284680 (The Pile)

Max Activating Token Index: 561