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

Dataset: The Pile

Neuron 1631 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: 7.1720. Min Range: -7.1720

Max Act: 7.1720. Min Act: -0.0000

Data Index: 1692467 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 7.1720. Min Range: -7.1720

Max Act: 6.3617. Min Act: -0.0000

Data Index: 1140244 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 7.1720. Min Range: -7.1720

Max Act: 5.9247. Min Act: -0.0000

Data Index: 1151067 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 7.1720. Min Range: -7.1720

Max Act: 5.1786. Min Act: -0.0000

Data Index: 119184 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.8575. Min Act: -0.0000

Data Index: 324180 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.5223. Min Act: -0.0000

Data Index: 1025251 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.6984. Min Act: -0.0000

Data Index: 1253386 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.1469. Min Act: -0.0000

Data Index: 896220 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.4792. Min Act: -0.0000

Data Index: 322550 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.6075. Min Act: -0.0000

Data Index: 1845546 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.5933. Min Act: -0.0000

Data Index: 1877488 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.2632. Min Act: -0.0000

Data Index: 1651846 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.5902. Min Act: -0.0000

Data Index: 350231 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.3837. Min Act: -0.0000

Data Index: 1240741 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 7.1720. Min Range: -7.1720

Max Act: 3.9594. Min Act: -0.0000

Data Index: 452966 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 7.1720. Min Range: -7.1720

Max Act: 3.9446. Min Act: -0.0000

Data Index: 1805649 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 7.1720. Min Range: -7.1720

Max Act: 3.7206. Min Act: -0.0000

Data Index: 1958643 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.0762. Min Act: -0.0000

Data Index: 44934 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 7.1720. Min Range: -7.1720

Max Act: 4.0717. Min Act: -0.0000

Data Index: 1694518 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 7.1720. Min Range: -7.1720

Max Act: 3.8458. Min Act: -0.0000

Data Index: 1251648 (The Pile)

Max Activating Token Index: 444