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

Dataset: The Pile

Neuron 3369 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: 1.0338. Min Range: -1.0338

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1683057 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.9869. Min Act: -0.0000

Data Index: 610587 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1566851 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1183182 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8837. Min Act: 0.0000

Data Index: 1003530 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1544867 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1661355 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8065. Min Act: -0.0000

Data Index: 977349 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8370. Min Act: 0.0000

Data Index: 944243 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.9104. Min Act: -0.0000

Data Index: 248360 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8045. Min Act: -0.0000

Data Index: 965426 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1763244 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1488336 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1601377 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7977. Min Act: -0.0000

Data Index: 640793 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8284. Min Act: -0.0000

Data Index: 608398 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1111792 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7955. Min Act: -0.0000

Data Index: 677548 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8135. Min Act: -0.0000

Data Index: 338861 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1436293 (The Pile)

Max Activating Token Index: 102