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

Dataset: The Pile

Neuron 3189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.8975. Min Act: -0.0000

Data Index: 779136 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.7644. Min Act: -0.0000

Data Index: 1200003 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.7448. Min Act: -0.0000

Data Index: 998725 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.7274. Min Act: -0.0000

Data Index: 1626369 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.6561. Min Act: -0.0000

Data Index: 1660646 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.6736. Min Act: -0.0000

Data Index: 1756518 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.6553. Min Act: -0.0000

Data Index: 1557658 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.4884. Min Act: -0.0000

Data Index: 1550914 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.4766. Min Act: -0.0000

Data Index: 213337 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.5816. Min Act: -0.0000

Data Index: 1283015 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.4136. Min Act: -0.0000

Data Index: 436140 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.4108. Min Act: -0.0000

Data Index: 773786 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.5050. Min Act: -0.0000

Data Index: 1521887 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.5167. Min Act: -0.0000

Data Index: 436403 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.3164. Min Act: -0.0000

Data Index: 1066205 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.6538. Min Act: -0.0000

Data Index: 391926 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.0711. Min Act: -0.0000

Data Index: 1925478 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.3258. Min Act: -0.0000

Data Index: 1625517 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.4642. Min Act: -0.0000

Data Index: 1322287 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 3.8975. Min Range: -3.8975

Max Act: 3.3076. Min Act: -0.0000

Data Index: 1169909 (The Pile)

Max Activating Token Index: 961