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

Dataset: The Pile

Neuron 654 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1028592 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1491076 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1930839 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5278. Min Act: -0.0000

Data Index: 908927 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1516774 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1638912 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1268188 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4820. Min Act: -0.0000

Data Index: 416755 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1262354 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1864300 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1171343 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1766293 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5126. Min Act: -0.0000

Data Index: 761592 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1605516 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1345366 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4416. Min Act: -0.0000

Data Index: 550074 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1139541 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4200. Min Act: -0.0000

Data Index: 76583 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1728119 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1043772 (The Pile)

Max Activating Token Index: 407