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

Dataset: The Pile

Neuron 4331 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: 3.7215. Min Range: -3.7215

Max Act: 3.7215. Min Act: -0.0000

Data Index: 1176022 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.5991. Min Act: -0.0000

Data Index: 982364 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.6460. Min Act: -0.0000

Data Index: 1203966 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.7971. Min Act: -0.0000

Data Index: 208255 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.7388. Min Act: -0.0000

Data Index: 212772 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.4849. Min Act: -0.0000

Data Index: 499329 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.6967. Min Act: -0.0000

Data Index: 1436782 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.8163. Min Act: -0.0000

Data Index: 1424248 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.3832. Min Act: -0.0000

Data Index: 1274941 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1301991 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.4335. Min Act: -0.0000

Data Index: 881850 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.3468. Min Act: -0.0000

Data Index: 1317072 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.5618. Min Act: -0.0000

Data Index: 1546463 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.4379. Min Act: -0.0000

Data Index: 1094798 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.7113. Min Act: -0.0000

Data Index: 1240848 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1468013 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.6044. Min Act: -0.0000

Data Index: 1500670 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.5611. Min Act: -0.0000

Data Index: 984694 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.4020. Min Act: -0.0000

Data Index: 765389 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 3.7215. Min Range: -3.7215

Max Act: 2.2821. Min Act: -0.0000

Data Index: 1047094 (The Pile)

Max Activating Token Index: 62