Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.3083. Min Act: -0.0000

Data Index: 590849 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1637487 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1102. Min Act: -0.0000

Data Index: 407609 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0775. Min Act: -0.0000

Data Index: 334483 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1886957 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1681287 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1387079 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1457562 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1874180 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0293. Min Act: -0.0000

Data Index: 244141 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1128270 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0482. Min Act: -0.0000

Data Index: 574733 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9978. Min Act: -0.0000

Data Index: 768185 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0870. Min Act: -0.0000

Data Index: 807406 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0468. Min Act: -0.0000

Data Index: 621897 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9855. Min Act: -0.0000

Data Index: 221905 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9750. Min Act: -0.0000

Data Index: 774253 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1782849 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9098. Min Act: -0.0000

Data Index: 490111 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0898. Min Act: -0.0000

Data Index: 591796 (The Pile)

Max Activating Token Index: 190