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

Dataset: The Pile

Neuron 4045 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8566. Min Act: -0.0000

Data Index: 683280 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1218225 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7872. Min Act: -0.0000

Data Index: 858949 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7356. Min Act: -0.0000

Data Index: 958026 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1222998 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7816. Min Act: -0.0000

Data Index: 401678 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1604399 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7546. Min Act: -0.0000

Data Index: 69167 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7618. Min Act: -0.0000

Data Index: 444909 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7616. Min Act: -0.0000

Data Index: 928674 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1449795 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7601. Min Act: -0.0000

Data Index: 885057 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7465. Min Act: -0.0000

Data Index: 87852 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6750. Min Act: -0.0000

Data Index: 983863 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1898227 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6947. Min Act: -0.0000

Data Index: 908105 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7015. Min Act: -0.0000

Data Index: 965858 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1227584 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1985263 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1078317 (The Pile)

Max Activating Token Index: 487