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

Dataset: The Pile

Neuron 955 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: 1.0009. Min Range: -1.0009

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1031140 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1146187 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9323. Min Act: -0.0000

Data Index: 621374 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8650. Min Act: -0.0000

Data Index: 688615 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1273821 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9140. Min Act: -0.0000

Data Index: 477984 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9415. Min Act: -0.0000

Data Index: 326491 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1101007 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1130624 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8584. Min Act: -0.0000

Data Index: 737316 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9173. Min Act: -0.0000

Data Index: 685982 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8658. Min Act: -0.0000

Data Index: 242713 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8911. Min Act: -0.0000

Data Index: 827220 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1697598 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9163. Min Act: 0.0000

Data Index: 1659585 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8319. Min Act: 0.0000

Data Index: 1954207 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1420621 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1124717 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8715. Min Act: 0.0000

Data Index: 1432530 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1169994 (The Pile)

Max Activating Token Index: 819