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

Dataset: The Pile

Neuron 4735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1540065 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1111115 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1606574 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7293. Min Act: -0.0000

Data Index: 654177 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1615627 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1085839 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1080907 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5426. Min Act: -0.0000

Data Index: 596147 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5462. Min Act: -0.0000

Data Index: 629490 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5044. Min Act: -0.0000

Data Index: 29961 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1946598 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4315. Min Act: -0.0000

Data Index: 858592 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1128469 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4479. Min Act: -0.0000

Data Index: 645074 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1126639 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1432874 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1561965 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.3990. Min Act: -0.0000

Data Index: 587812 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1183555 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.4097. Min Act: -0.0000

Data Index: 221755 (The Pile)

Max Activating Token Index: 634