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

Dataset: The Pile

Neuron 3679 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: 1.3241. Min Range: -1.3241

Max Act: 1.3241. Min Act: -0.0000

Data Index: 153020 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.2057. Min Act: -0.0000

Data Index: 946262 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.2796. Min Act: -0.0000

Data Index: 168863 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.2412. Min Act: -0.0000

Data Index: 165884 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.2811. Min Act: -0.0000

Data Index: 274082 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.0878. Min Act: -0.0001

Data Index: 383559 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1127471 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.2221. Min Act: -0.0000

Data Index: 571099 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1265002 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1604699 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1451316 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1614. Min Act: -0.0000

Data Index: 294712 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1540. Min Act: -0.0000

Data Index: 403158 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1849805 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.0130. Min Act: -0.0000

Data Index: 178982 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.9495. Min Act: -0.0000

Data Index: 674110 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1296. Min Act: -0.0000

Data Index: 859940 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.9443. Min Act: -0.0000

Data Index: 468618 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1427967 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.0562. Min Act: -0.0000

Data Index: 116889 (The Pile)

Max Activating Token Index: 352