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

Dataset: The Pile

Neuron 3376 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: 0.5728. Min Range: -0.5728

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1199502 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.5169. Min Act: -0.0000

Data Index: 249876 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1619876 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.5094. Min Act: 0.0000

Data Index: 1216011 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4838. Min Act: -0.0000

Data Index: 124878 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4709. Min Act: -0.0000

Data Index: 472937 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4688. Min Act: 0.0000

Data Index: 882158 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1700359 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1751209 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4684. Min Act: 0.0000

Data Index: 1425692 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1817228 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1825049 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1387559 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4140. Min Act: -0.0000

Data Index: 299470 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1634195 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3990. Min Act: -0.0000

Data Index: 756246 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1426747 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4219. Min Act: -0.0000

Data Index: 736764 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4177. Min Act: -0.0000

Data Index: 541210 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4062. Min Act: -0.0000

Data Index: 265450 (The Pile)

Max Activating Token Index: 542