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

Dataset: The Pile

Neuron 4822 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: 1.6338. Min Range: -1.6338

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1075810 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5216. Min Act: -0.0000

Data Index: 58092 (The Pile)

Max Activating Token Index: 60

Text #2

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1533590 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.2905. Min Act: -0.0000

Data Index: 75300 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.1224. Min Act: -0.0000

Data Index: 210650 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.0621. Min Act: -0.0000

Data Index: 296948 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.1630. Min Act: -0.0000

Data Index: 578626 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9770. Min Act: -0.0000

Data Index: 306847 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1266511 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.0407. Min Act: -0.0000

Data Index: 12054 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1194519 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1184815 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1363425 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.0522. Min Act: -0.0000

Data Index: 834371 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1313638 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1628900 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1866447 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9497. Min Act: -0.0000

Data Index: 557816 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 1.6338. Min Range: -1.6338

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1330802 (The Pile)

Max Activating Token Index: 17