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

Dataset: The Pile

Neuron 123 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.6737. Min Act: -0.0000

Data Index: 267847 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1465597 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1402118 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1761444 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1945446 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2622. Min Act: -0.0000

Data Index: 214682 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1291634 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1655610 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1488445 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1739991 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.0677. Min Act: -0.0000

Data Index: 778753 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1708. Min Act: -0.0000

Data Index: 696727 (The Pile)

Max Activating Token Index: 168

Text #12

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1232710 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1127689 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.2305. Min Act: -0.0000

Data Index: 399203 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.0330. Min Act: -0.0000

Data Index: 857983 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1220. Min Act: -0.0000

Data Index: 948653 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1845. Min Act: -0.0000

Data Index: 379898 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1569572 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 1.6737. Min Range: -1.6737

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1110937 (The Pile)

Max Activating Token Index: 603