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

Dataset: The Pile

Neuron 509 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: 1.8186. Min Range: -1.8186

Max Act: 1.8186. Min Act: -0.0000

Data Index: 1330685 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0865. Min Act: -0.0000

Data Index: 829991 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1117988 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1743644 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1539498 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.5574. Min Act: -0.0000

Data Index: 330763 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6278. Min Act: -0.0000

Data Index: 48656 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1137431 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6573. Min Act: -0.0000

Data Index: 600336 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6224. Min Act: -0.0000

Data Index: 792185 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6745. Min Act: -0.0000

Data Index: 146989 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.7029. Min Act: -0.0000

Data Index: 338369 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.7537. Min Act: -0.0000

Data Index: 811015 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1146054 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1918639 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6740. Min Act: -0.0000

Data Index: 15530 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1811933 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1663974 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1849403 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.3879. Min Act: -0.0000

Data Index: 367738 (The Pile)

Max Activating Token Index: 148