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

Dataset: The Pile

Neuron 430 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: 3.5120. Min Range: -3.5120

Max Act: 3.5120. Min Act: -0.0000

Data Index: 752493 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.4830. Min Act: -0.0000

Data Index: 1849702 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.3287. Min Act: -0.0000

Data Index: 1341390 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.0425. Min Act: -0.0000

Data Index: 112340 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.2813. Min Act: -0.0000

Data Index: 760755 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.2728. Min Act: -0.0000

Data Index: 299418 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.2133. Min Act: -0.0000

Data Index: 1400477 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.1823. Min Act: -0.0000

Data Index: 1671610 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.0084. Min Act: -0.0000

Data Index: 1801905 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.0240. Min Act: -0.0000

Data Index: 128023 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 3.5120. Min Range: -3.5120

Max Act: 2.9693. Min Act: -0.0000

Data Index: 187852 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.1412. Min Act: -0.0000

Data Index: 1128933 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 3.5120. Min Range: -3.5120

Max Act: 2.9950. Min Act: -0.0000

Data Index: 1431225 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.1260. Min Act: -0.0000

Data Index: 1974946 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.1180. Min Act: -0.0000

Data Index: 1499182 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 3.5120. Min Range: -3.5120

Max Act: 2.9660. Min Act: -0.0000

Data Index: 1076410 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 3.5120. Min Range: -3.5120

Max Act: 2.9431. Min Act: -0.0000

Data Index: 1895392 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.0708. Min Act: -0.0000

Data Index: 697912 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 3.5120. Min Range: -3.5120

Max Act: 2.9767. Min Act: -0.0000

Data Index: 1252336 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 3.5120. Min Range: -3.5120

Max Act: 3.1233. Min Act: -0.0000

Data Index: 539957 (The Pile)

Max Activating Token Index: 912