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

Dataset: The Pile

Neuron 2530 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: 0.4876. Min Range: -0.4876

Max Act: 0.4876. Min Act: -0.0000

Data Index: 283981 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1530198 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1159674 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1119947 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1158780 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3690. Min Act: -0.0000

Data Index: 73912 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1799766 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4016. Min Act: -0.0000

Data Index: 756702 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1257433 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.2918. Min Act: -0.0000

Data Index: 989895 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3216. Min Act: -0.0000

Data Index: 118922 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1876381 (The Pile)

Max Activating Token Index: 727

Text #12

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1069312 (The Pile)

Max Activating Token Index: 995

Text #13

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3386. Min Act: -0.0000

Data Index: 498858 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3380. Min Act: -0.0000

Data Index: 310446 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3259. Min Act: -0.0000

Data Index: 798093 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3082. Min Act: -0.0000

Data Index: 188115 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.2758. Min Act: -0.0000

Data Index: 696973 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1367605 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1213897 (The Pile)

Max Activating Token Index: 1015