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

Dataset: The Pile

Neuron 2500 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1810834 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2610. Min Act: -0.0000

Data Index: 475075 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2539. Min Act: -0.0000

Data Index: 719555 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1875145 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1906170 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1603. Min Act: -0.0000

Data Index: 418919 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1618622 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1167814 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1575441 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1490. Min Act: -0.0000

Data Index: 774978 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1435. Min Act: -0.0000

Data Index: 857892 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1360. Min Act: -0.0000

Data Index: 794594 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1456. Min Act: -0.0000

Data Index: 590785 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1507. Min Act: -0.0000

Data Index: 435938 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1542. Min Act: -0.0000

Data Index: 242227 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1521290 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1518362 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1267. Min Act: -0.0000

Data Index: 991197 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1465. Min Act: -0.0000

Data Index: 779932 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1326. Min Act: -0.0000

Data Index: 813954 (The Pile)

Max Activating Token Index: 516