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

Dataset: The Pile

Neuron 4249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1734577 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2981. Min Act: 0.0000

Data Index: 705010 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1053077 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1383881 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1710621 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1943. Min Act: -0.0000

Data Index: 421096 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1485366 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1679. Min Act: -0.0000

Data Index: 849769 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1580. Min Act: -0.0000

Data Index: 677479 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1338808 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1927. Min Act: -0.0000

Data Index: 95270 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1903. Min Act: -0.0000

Data Index: 859997 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1484. Min Act: -0.0000

Data Index: 92509 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1641. Min Act: -0.0000

Data Index: 166649 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1733118 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1143. Min Act: -0.0000

Data Index: 996494 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1440186 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1237535 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1819201 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.1404. Min Act: -0.0000

Data Index: 843856 (The Pile)

Max Activating Token Index: 819