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

Dataset: The Pile

Neuron 3422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.6707. Min Act: -0.0000

Data Index: 844458 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5862. Min Act: -0.0000

Data Index: 815918 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1652532 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1534331 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1026823 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5213. Min Act: -0.0000

Data Index: 154703 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5073. Min Act: -0.0000

Data Index: 674730 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5099. Min Act: -0.0000

Data Index: 592892 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1776413 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1116995 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4865. Min Act: -0.0000

Data Index: 694751 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1878605 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4540. Min Act: -0.0000

Data Index: 1883167 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1787873 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4608. Min Act: -0.0000

Data Index: 643092 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.5340. Min Act: -0.0000

Data Index: 312169 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.3603. Min Act: -0.0000

Data Index: 1706578 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4343. Min Act: -0.0000

Data Index: 142535 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1434004 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.6707. Min Range: -1.6707

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1010046 (The Pile)

Max Activating Token Index: 255