Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2041 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.8286. Min Act: -0.0000

Data Index: 887412 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.8272. Min Act: -0.0000

Data Index: 598861 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1550034 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1289571 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1727393 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6784. Min Act: -0.0000

Data Index: 244923 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6771. Min Act: -0.0000

Data Index: 97353 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6783. Min Act: -0.0000

Data Index: 756564 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6872. Min Act: -0.0000

Data Index: 773629 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6970. Min Act: -0.0000

Data Index: 645521 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6422. Min Act: -0.0000

Data Index: 41226 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1808546 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1991838 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6116. Min Act: -0.0000

Data Index: 111816 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6353. Min Act: -0.0000

Data Index: 55854 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6215. Min Act: 0.0000

Data Index: 383314 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1140279 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6087. Min Act: -0.0000

Data Index: 162494 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1490599 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5698. Min Act: -0.0000

Data Index: 964506 (The Pile)

Max Activating Token Index: 607