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

Dataset: The Pile

Neuron 3427 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: 1.0294. Min Range: -1.0294

Max Act: 1.0294. Min Act: -0.0000

Data Index: 139123 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1167012 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8379. Min Act: -0.0000

Data Index: 612832 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1805082 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7963. Min Act: -0.0000

Data Index: 325775 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1564239 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7974. Min Act: -0.0000

Data Index: 9706 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7733. Min Act: -0.0000

Data Index: 998893 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7945. Min Act: -0.0000

Data Index: 342210 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7856. Min Act: -0.0000

Data Index: 581490 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1682611 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1336351 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1866912 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1236370 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7730. Min Act: -0.0000

Data Index: 884632 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1708132 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7423. Min Act: -0.0000

Data Index: 548790 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1976239 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1596162 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.0294. Min Range: -1.0294

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1502463 (The Pile)

Max Activating Token Index: 217