Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3262 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.1393. Min Act: -0.0000

Data Index: 1499006 (The Pile)

Max Activating Token Index: 62

Text #1

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1736260 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.1319. Min Act: 0.0001

Data Index: 1807072 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0624. Min Act: -0.0000

Data Index: 729794 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1171098 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1407282 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1900433 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1588738 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1206105 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0218. Min Act: -0.0000

Data Index: 688904 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0483. Min Act: 0.0000

Data Index: 959974 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1009969 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 1.1393. Min Range: -1.1393

Max Act: 1.0357. Min Act: 0.0000

Data Index: 1298798 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1246885 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1882610 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1381491 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1240926 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9707. Min Act: -0.0000

Data Index: 671247 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9752. Min Act: 0.0000

Data Index: 1158338 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 1.1393. Min Range: -1.1393

Max Act: 0.9473. Min Act: -0.0000

Data Index: 467597 (The Pile)

Max Activating Token Index: 436