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

Dataset: The Pile

Neuron 593 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.4049. Min Act: -0.0000

Data Index: 386021 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.3455. Min Act: 0.0000

Data Index: 1722211 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1204009 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1701959 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.3186. Min Act: -0.0000

Data Index: 445553 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.4456. Min Act: -0.0000

Data Index: 213088 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2898. Min Act: -0.0000

Data Index: 746362 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.3154. Min Act: 0.0000

Data Index: 791093 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1721. Min Act: -0.0000

Data Index: 240461 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2672. Min Act: 0.0001

Data Index: 1818977 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1758851 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1010322 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1430. Min Act: -0.0000

Data Index: 154994 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1497667 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1202. Min Act: -0.0000

Data Index: 113169 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1894. Min Act: 0.0000

Data Index: 1662034 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0861. Min Act: 0.0000

Data Index: 1622555 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1904398 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 1.4456. Min Range: -1.4456

Max Act: 1.0375. Min Act: -0.0000

Data Index: 790778 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 1.4456. Min Range: -1.4456

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1446615 (The Pile)

Max Activating Token Index: 909