Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 999 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1002931 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1327980 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6277. Min Act: -0.0000

Data Index: 679071 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1813671 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1182837 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5755. Min Act: -0.0001

Data Index: 1990472 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5840. Min Act: -0.0000

Data Index: 745792 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1871572 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1943364 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1593243 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.4739. Min Act: -0.0000

Data Index: 829967 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5064. Min Act: -0.0000

Data Index: 88401 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5300. Min Act: -0.0000

Data Index: 797393 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5070. Min Act: -0.0000

Data Index: 219554 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5609. Min Act: -0.0000

Data Index: 26816 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.4885. Min Act: -0.0000

Data Index: 600624 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1643708 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5057. Min Act: -0.0000

Data Index: 222361 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.5199. Min Act: -0.0001

Data Index: 35421 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.4765. Min Act: -0.0000

Data Index: 943578 (The Pile)

Max Activating Token Index: 679