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

Dataset: The Pile

Neuron 2717 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1062130 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6368. Min Act: -0.0000

Data Index: 899735 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1230265 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1842061 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5033. Min Act: -0.0000

Data Index: 170964 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5089. Min Act: -0.0000

Data Index: 855942 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4663. Min Act: -0.0000

Data Index: 695705 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1274054 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1806474 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4855. Min Act: -0.0000

Data Index: 610693 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1716909 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1850150 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5207. Min Act: -0.0000

Data Index: 799971 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5052. Min Act: -0.0000

Data Index: 403575 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5329. Min Act: -0.0000

Data Index: 673064 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.3512. Min Act: 0.0000

Data Index: 545822 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4967. Min Act: -0.0000

Data Index: 718414 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1561360 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5041. Min Act: -0.0000

Data Index: 290334 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4562. Min Act: -0.0000

Data Index: 143045 (The Pile)

Max Activating Token Index: 910