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

Dataset: The Pile

Neuron 845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1706756 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.6577. Min Act: -0.0000

Data Index: 1083256 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1523030 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1394842 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.6332. Min Act: -0.0000

Data Index: 491555 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4471. Min Act: -0.0000

Data Index: 26673 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1838506 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1158054 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1632361 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1862483 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4444. Min Act: -0.0000

Data Index: 386013 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4271. Min Act: -0.0000

Data Index: 908436 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1863946 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1929332 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1106913 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1368573 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.4066. Min Act: -0.0000

Data Index: 928874 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2786. Min Act: -0.0000

Data Index: 1606881 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1210208 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2754. Min Act: -0.0000

Data Index: 876624 (The Pile)

Max Activating Token Index: 198