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

Dataset: The Pile

Neuron 2269 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: 1.7809. Min Range: -1.7809

Max Act: 1.7635. Min Act: -0.0000

Data Index: 241132 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.7809. Min Act: -0.0000

Data Index: 136571 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6635. Min Act: -0.0000

Data Index: 10422 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1479809 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1735835 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6177. Min Act: -0.0000

Data Index: 1943660 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6059. Min Act: -0.0000

Data Index: 99739 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1608612 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.5339. Min Act: -0.0000

Data Index: 712113 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.5937. Min Act: -0.0000

Data Index: 1382715 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1200093 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4030. Min Act: -0.0000

Data Index: 1557992 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4480. Min Act: -0.0000

Data Index: 543400 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4192. Min Act: -0.0000

Data Index: 756028 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4402. Min Act: -0.0000

Data Index: 356355 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1426937 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1999817 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.5234. Min Act: -0.0000

Data Index: 309579 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.5228. Min Act: -0.0000

Data Index: 1784105 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4941. Min Act: -0.0000

Data Index: 973720 (The Pile)

Max Activating Token Index: 539