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

Dataset: The Pile

Neuron 658 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: 3.3016. Min Range: -3.3016

Max Act: 3.3016. Min Act: -0.0000

Data Index: 1979499 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.2841. Min Act: -0.0000

Data Index: 1435076 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.2196. Min Act: -0.0000

Data Index: 198297 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.0468. Min Act: -0.0000

Data Index: 56316 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.9087. Min Act: -0.0000

Data Index: 1664257 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.0760. Min Act: -0.0000

Data Index: 1391384 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.0545. Min Act: -0.0000

Data Index: 1818 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.0321. Min Act: -0.0000

Data Index: 1609051 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.0164. Min Act: -0.0000

Data Index: 240690 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.8727. Min Act: -0.0000

Data Index: 449334 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.1444. Min Act: -0.0000

Data Index: 1580917 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.9421. Min Act: -0.0000

Data Index: 1346007 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.9555. Min Act: -0.0000

Data Index: 559162 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.8090. Min Act: -0.0000

Data Index: 1385569 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.7876. Min Act: -0.0000

Data Index: 948622 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 3.3016. Min Range: -3.3016

Max Act: 3.0678. Min Act: -0.0000

Data Index: 1862004 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.9163. Min Act: -0.0000

Data Index: 1079850 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.9070. Min Act: -0.0000

Data Index: 1752738 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.9096. Min Act: -0.0000

Data Index: 1479775 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 3.3016. Min Range: -3.3016

Max Act: 2.8876. Min Act: -0.0000

Data Index: 691944 (The Pile)

Max Activating Token Index: 508