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

Dataset: The Pile

Neuron 989 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: 1.8730. Min Range: -1.8730

Max Act: 1.8730. Min Act: -0.0000

Data Index: 88466 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1682091 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.6250. Min Act: -0.0000

Data Index: 757751 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.6439. Min Act: -0.0000

Data Index: 499240 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.6660. Min Act: -0.0000

Data Index: 1029917 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1434340 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.6029. Min Act: -0.0000

Data Index: 246284 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4619. Min Act: -0.0000

Data Index: 724545 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1892535 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1689998 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1224799 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.3506. Min Act: -0.0000

Data Index: 688115 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1805712 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1666920 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4097. Min Act: -0.0000

Data Index: 1436759 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.3151. Min Act: -0.0000

Data Index: 1312273 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1928657 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4039. Min Act: -0.0000

Data Index: 365111 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1231676 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2751. Min Act: -0.0000

Data Index: 293333 (The Pile)

Max Activating Token Index: 840