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

Dataset: The Pile

Neuron 4588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1080. Min Range: -1.1080

Max Act: 1.1080. Min Act: -0.0000

Data Index: 948908 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8606. Min Act: -0.0000

Data Index: 377750 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1882226 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8245. Min Act: -0.0000

Data Index: 224569 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8547. Min Act: -0.0000

Data Index: 737816 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8097. Min Act: -0.0000

Data Index: 191945 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1777168 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1517395 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1985963 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1465044 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8017. Min Act: -0.0000

Data Index: 337532 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1198048 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7492. Min Act: -0.0000

Data Index: 703190 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.8031. Min Act: -0.0000

Data Index: 186550 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7477. Min Act: -0.0000

Data Index: 289707 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7708. Min Act: -0.0000

Data Index: 799600 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1912473 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7584. Min Act: -0.0000

Data Index: 622455 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1734796 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 1.1080. Min Range: -1.1080

Max Act: 0.6921. Min Act: -0.0000

Data Index: 839506 (The Pile)

Max Activating Token Index: 76