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

Dataset: The Pile

Neuron 437 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: 1.2504. Min Range: -1.2504

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1443182 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1154835 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1868108 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9467. Min Act: -0.0000

Data Index: 192072 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1469115 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9564. Min Act: -0.0000

Data Index: 456750 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9059. Min Act: -0.0000

Data Index: 673862 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8311. Min Act: -0.0000

Data Index: 265030 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8342. Min Act: -0.0000

Data Index: 247328 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1781097 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8117. Min Act: -0.0000

Data Index: 750525 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7805. Min Act: -0.0000

Data Index: 77743 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1309492 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7420. Min Act: -0.0000

Data Index: 847792 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7865. Min Act: -0.0000

Data Index: 244451 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7917. Min Act: -0.0000

Data Index: 958551 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1653696 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7680. Min Act: -0.0000

Data Index: 240533 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1187648 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7174. Min Act: -0.0000

Data Index: 596975 (The Pile)

Max Activating Token Index: 323