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

Dataset: The Pile

Neuron 1188 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: 1.1303. Min Range: -1.1303

Max Act: 1.1303. Min Act: -0.0000

Data Index: 540103 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 1.1303. Min Range: -1.1303

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1362657 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9959. Min Act: -0.0000

Data Index: 97112 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9444. Min Act: -0.0000

Data Index: 517539 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9802. Min Act: -0.0000

Data Index: 770638 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1964373 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1046854 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1375960 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1819465 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1898814 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8793. Min Act: -0.0000

Data Index: 566487 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8664. Min Act: -0.0000

Data Index: 654185 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1774165 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8813. Min Act: -0.0000

Data Index: 160877 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1686187 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1252760 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1929481 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8868. Min Act: -0.0000

Data Index: 582176 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1797231 (The Pile)

Max Activating Token Index: 5

Text #19

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1874267 (The Pile)

Max Activating Token Index: 51