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

Dataset: The Pile

Neuron 3461 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: 0.6830. Min Range: -0.6830

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1042473 (The Pile)

Max Activating Token Index: 889

Text #1

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1627927 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5336. Min Act: -0.0000

Data Index: 674484 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5122. Min Act: -0.0000

Data Index: 947372 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4723. Min Act: -0.0000

Data Index: 80658 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4848. Min Act: 0.0000

Data Index: 1673755 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1258893 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4498. Min Act: -0.0000

Data Index: 165215 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1670203 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.5002. Min Act: -0.0000

Data Index: 140495 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1365595 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1870795 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4250. Min Act: -0.0000

Data Index: 46100 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1106971 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1873568 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1559013 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3842. Min Act: 0.0001

Data Index: 205725 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3772. Min Act: -0.0000

Data Index: 350331 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1956754 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 0.6830. Min Range: -0.6830

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1247374 (The Pile)

Max Activating Token Index: 193