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

Dataset: The Pile

Neuron 2868 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: 3.0656. Min Range: -3.0656

Max Act: 3.0656. Min Act: -0.0000

Data Index: 595989 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1670168 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.2661. Min Act: -0.0000

Data Index: 1803552 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.2405. Min Act: -0.0000

Data Index: 1174362 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.2193. Min Act: -0.0000

Data Index: 1987277 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.2307. Min Act: -0.0000

Data Index: 1893224 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.1514. Min Act: -0.0000

Data Index: 1048830 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.1103. Min Act: -0.0000

Data Index: 443452 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.2551. Min Act: -0.0000

Data Index: 1552072 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.1823. Min Act: -0.0000

Data Index: 33212 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.0282. Min Act: -0.0000

Data Index: 1963454 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.0182. Min Act: -0.0000

Data Index: 601644 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 3.0656. Min Range: -3.0656

Max Act: 1.9927. Min Act: -0.0000

Data Index: 709258 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 3.0656. Min Range: -3.0656

Max Act: 1.9836. Min Act: -0.0000

Data Index: 1604362 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.1030. Min Act: -0.0000

Data Index: 1022579 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 3.0656. Min Range: -3.0656

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1743092 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.0291. Min Act: -0.0000

Data Index: 1708131 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 3.0656. Min Range: -3.0656

Max Act: 2.0118. Min Act: -0.0000

Data Index: 240646 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 3.0656. Min Range: -3.0656

Max Act: 1.8136. Min Act: -0.0000

Data Index: 643043 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 3.0656. Min Range: -3.0656

Max Act: 1.7830. Min Act: -0.0000

Data Index: 421953 (The Pile)

Max Activating Token Index: 987