Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8884. Min Act: -0.0000

Data Index: 932600 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1467943 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.9058. Min Act: -0.0000

Data Index: 430703 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1232900 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1888222 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8464. Min Act: -0.0000

Data Index: 69166 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1207650 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1393601 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6992. Min Act: -0.0000

Data Index: 763447 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1011241 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1821022 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1568757 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1875709 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1086428 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1358074 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1977256 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6860. Min Act: -0.0000

Data Index: 429329 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6927. Min Act: -0.0000

Data Index: 890450 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6708. Min Act: -0.0000

Data Index: 30760 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.9530. Min Range: -0.9530

Max Act: 0.6306. Min Act: -0.0000

Data Index: 12480 (The Pile)

Max Activating Token Index: 771