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

Dataset: The Pile

Neuron 4911 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.6081. Min Act: -0.0000

Data Index: 1407811 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.5301. Min Act: -0.0000

Data Index: 51257 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.4108. Min Act: -0.0000

Data Index: 1935863 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.3886. Min Act: -0.0000

Data Index: 834971 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.2672. Min Act: -0.0000

Data Index: 1629096 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.1752. Min Act: -0.0000

Data Index: 115773 (The Pile)

Max Activating Token Index: 68

Text #6

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.0928. Min Act: -0.0000

Data Index: 1731625 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.8165. Min Act: -0.0000

Data Index: 262568 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.9791. Min Act: -0.0000

Data Index: 1014365 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 3.6081. Min Range: -3.6081

Max Act: 3.0513. Min Act: -0.0000

Data Index: 338416 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.8503. Min Act: -0.0000

Data Index: 1526661 (The Pile)

Max Activating Token Index: 840

Text #11

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.7729. Min Act: -0.0000

Data Index: 76280 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.7564. Min Act: -0.0000

Data Index: 1436002 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.7013. Min Act: -0.0000

Data Index: 1558079 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.8025. Min Act: -0.0000

Data Index: 1248812 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.6887. Min Act: -0.0000

Data Index: 247481 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.6916. Min Act: -0.0000

Data Index: 356993 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.6520. Min Act: -0.0000

Data Index: 10571 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.7284. Min Act: -0.0000

Data Index: 1439303 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 3.6081. Min Range: -3.6081

Max Act: 2.7874. Min Act: -0.0000

Data Index: 1205241 (The Pile)

Max Activating Token Index: 973