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

Dataset: The Pile

Neuron 3824 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: 1.1060. Min Range: -1.1060

Max Act: 1.1060. Min Act: -0.0000

Data Index: 64086 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1394305 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9277. Min Act: -0.0000

Data Index: 408533 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8848. Min Act: -0.0000

Data Index: 847898 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1825365 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8251. Min Act: -0.0000

Data Index: 412423 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1547945 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9389. Min Act: -0.0000

Data Index: 50429 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1788016 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1080239 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8310. Min Act: -0.0000

Data Index: 84642 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1297817 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1821932 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1092771 (The Pile)

Max Activating Token Index: 305

Text #14

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1939735 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9139. Min Act: -0.0000

Data Index: 777794 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8473. Min Act: -0.0000

Data Index: 516607 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8092. Min Act: -0.0000

Data Index: 808496 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7526. Min Act: -0.0000

Data Index: 58156 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1950701 (The Pile)

Max Activating Token Index: 117