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

Dataset: The Pile

Neuron 4051 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: 1.2774. Min Range: -1.2774

Max Act: 1.2370. Min Act: -0.0000

Data Index: 689569 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1355805 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1791223 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0259. Min Act: -0.0000

Data Index: 760120 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 1.2774. Min Range: -1.2774

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1551948 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1353019 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1088534 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9762. Min Act: -0.0000

Data Index: 645501 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1487447 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1704307 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.7747. Min Act: -0.0000

Data Index: 415317 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1103785 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1160660 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1945182 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1712292 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1010737 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8171. Min Act: -0.0000

Data Index: 789208 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8182. Min Act: -0.0000

Data Index: 476567 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.9202. Min Act: -0.0000

Data Index: 434645 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 1.2774. Min Range: -1.2774

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1369009 (The Pile)

Max Activating Token Index: 970