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

Dataset: The Pile

Neuron 1776 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: 1.1149. Min Range: -1.1149

Max Act: 1.1024. Min Act: -0.0000

Data Index: 453312 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0205. Min Act: -0.0000

Data Index: 757430 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1816326 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0742. Min Act: -0.0000

Data Index: 179547 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.1149. Min Act: -0.0000

Data Index: 637240 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.1025. Min Act: -0.0000

Data Index: 301786 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0950. Min Act: -0.0000

Data Index: 47856 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0140. Min Act: -0.0000

Data Index: 554448 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1806168 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1466982 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0612. Min Act: -0.0000

Data Index: 295117 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9982. Min Act: -0.0000

Data Index: 697813 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9331. Min Act: -0.0000

Data Index: 759114 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1461976 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1605135 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1904970 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0778. Min Act: -0.0000

Data Index: 654235 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9830. Min Act: -0.0000

Data Index: 766932 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 1.1149. Min Range: -1.1149

Max Act: 1.0477. Min Act: -0.0000

Data Index: 835874 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 1.1149. Min Range: -1.1149

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1733608 (The Pile)

Max Activating Token Index: 90