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

Dataset: The Pile

Neuron 924 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: 0.9792. Min Range: -0.9792

Max Act: 0.9704. Min Act: -0.0000

Data Index: 252875 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9792. Min Act: -0.0000

Data Index: 300754 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1628582 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1600115 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1109724 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1596383 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8157. Min Act: 0.0000

Data Index: 1041166 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8691. Min Act: -0.0000

Data Index: 158942 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1680167 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8208. Min Act: -0.0000

Data Index: 871004 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1523164 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8164. Min Act: -0.0000

Data Index: 253222 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1681221 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.8228. Min Act: 0.0000

Data Index: 62689 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7918. Min Act: -0.0000

Data Index: 941622 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1209789 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7680. Min Act: -0.0000

Data Index: 676361 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1643750 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1103284 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 0.9792. Min Range: -0.9792

Max Act: 0.7577. Min Act: -0.0000

Data Index: 975890 (The Pile)

Max Activating Token Index: 767