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

Dataset: The Pile

Neuron 4601 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6670. Min Act: -0.0000

Data Index: 262291 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6174. Min Act: -0.0000

Data Index: 1369977 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1820228 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1462860 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3016. Min Act: -0.0000

Data Index: 821497 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1618630 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1525874 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1206. Min Act: -0.0000

Data Index: 882452 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1604. Min Act: -0.0000

Data Index: 586281 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.6670. Min Range: -1.6670

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1961840 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.2757. Min Act: -0.0000

Data Index: 987515 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1839. Min Act: -0.0000

Data Index: 502766 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1182. Min Act: 0.0000

Data Index: 1920185 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1174130 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.0636. Min Act: -0.0000

Data Index: 778307 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1451. Min Act: -0.0000

Data Index: 412504 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1019483 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.1143. Min Act: -0.0000

Data Index: 483257 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1036014 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.0399. Min Act: -0.0000

Data Index: 691257 (The Pile)

Max Activating Token Index: 159