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

Dataset: The Pile

Neuron 2412 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: 0.9010. Min Range: -0.9010

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1095773 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8561. Min Act: -0.0000

Data Index: 331714 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1486440 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1461707 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7127. Min Act: -0.0000

Data Index: 12701 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6504. Min Act: -0.0000

Data Index: 360500 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6609. Min Act: -0.0000

Data Index: 635979 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1447255 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5271. Min Act: -0.0000

Data Index: 764971 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5990. Min Act: -0.0000

Data Index: 141265 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6331. Min Act: -0.0000

Data Index: 359504 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1051023 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1187191 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1774251 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5396. Min Act: -0.0000

Data Index: 80061 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1363400 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1587341 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1351259 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6167. Min Act: -0.0000

Data Index: 630008 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1847999 (The Pile)

Max Activating Token Index: 789