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

Dataset: The Pile

Neuron 233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1205429 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1460. Min Act: -0.0000

Data Index: 89469 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1537. Min Act: -0.0000

Data Index: 48283 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1646058 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1220. Min Act: -0.0000

Data Index: 985878 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1305. Min Act: -0.0000

Data Index: 510011 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1023. Min Act: -0.0000

Data Index: 27619 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1999821 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1344. Min Act: -0.0000

Data Index: 200374 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1120773 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1393. Min Act: -0.0000

Data Index: 639961 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1815805 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1270. Min Act: -0.0000

Data Index: 262149 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1850816 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1012642 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1142. Min Act: -0.0000

Data Index: 404974 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1102. Min Act: -0.0000

Data Index: 669504 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1083. Min Act: -0.0000

Data Index: 226234 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1968222 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1088. Min Act: -0.0000

Data Index: 71654 (The Pile)

Max Activating Token Index: 654