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

Dataset: The Pile

Neuron 961 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1534032 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1125489 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7392. Min Act: -0.0000

Data Index: 628734 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7750. Min Act: -0.0000

Data Index: 934587 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7238. Min Act: -0.0000

Data Index: 921375 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1352129 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1054935 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1130826 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1824773 (The Pile)

Max Activating Token Index: 180

Text #9

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1567177 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1355205 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6673. Min Act: -0.0000

Data Index: 403920 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1205481 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6441. Min Act: -0.0000

Data Index: 10413 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1051245 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7043. Min Act: -0.0000

Data Index: 378868 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1022178 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6664. Min Act: -0.0000

Data Index: 857759 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1053450 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1272480 (The Pile)

Max Activating Token Index: 423