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

Dataset: The Pile

Neuron 2504 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2076. Min Range: -1.2076

Max Act: 1.2076. Min Act: -0.0000

Data Index: 1654015 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.2076. Min Range: -1.2076

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1440031 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 1.2076. Min Range: -1.2076

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1765115 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9142. Min Act: 0.0000

Data Index: 519419 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8158. Min Act: 0.0000

Data Index: 441481 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1597052 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7818. Min Act: -0.0000

Data Index: 565708 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7741. Min Act: -0.0000

Data Index: 633936 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7752. Min Act: -0.0000

Data Index: 438137 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1235236 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7300. Min Act: -0.0000

Data Index: 88846 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.6983. Min Act: -0.0000

Data Index: 671021 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1705786 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1872986 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1477195 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.5896. Min Act: -0.0000

Data Index: 418400 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.6499. Min Act: -0.0000

Data Index: 224281 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1069623 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1391114 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1236635 (The Pile)

Max Activating Token Index: 623