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

Dataset: The Pile

Neuron 2390 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: 1.2126. Min Range: -1.2126

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1926908 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1966160 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0882. Min Act: -0.0000

Data Index: 102181 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1304134 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1482428 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1971334 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8523. Min Act: -0.0000

Data Index: 397515 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7946. Min Act: -0.0000

Data Index: 15221 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1221452 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1024985 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7521. Min Act: -0.0000

Data Index: 238331 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1134581 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1506509 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8050. Min Act: -0.0000

Data Index: 832801 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1924482 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7797. Min Act: -0.0000

Data Index: 789878 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1396256 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1756118 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7802. Min Act: -0.0000

Data Index: 309920 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1369190 (The Pile)

Max Activating Token Index: 503