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

Dataset: The Pile

Neuron 1681 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8722. Min Act: -0.0000

Data Index: 92439 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8441. Min Act: -0.0000

Data Index: 1357345 (The Pile)

Max Activating Token Index: 335

Text #2

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7215. Min Act: -0.0000

Data Index: 357485 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6649. Min Act: -0.0000

Data Index: 246535 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7292. Min Act: -0.0000

Data Index: 500943 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1211310 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6163. Min Act: 0.0000

Data Index: 1465593 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1960007 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1968692 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6740. Min Act: 0.0000

Data Index: 337376 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6468. Min Act: 0.0000

Data Index: 523913 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1175817 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1424754 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6350. Min Act: -0.0000

Data Index: 534492 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1793368 (The Pile)

Max Activating Token Index: 414

Text #15

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8243. Min Act: -0.0000

Data Index: 1442104 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6239. Min Act: 0.0000

Data Index: 497119 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6253. Min Act: 0.0000

Data Index: 1659315 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5966. Min Act: -0.0000

Data Index: 1009995 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6849. Min Act: -0.0000

Data Index: 784953 (The Pile)

Max Activating Token Index: 473