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

Dataset: The Pile

Neuron 3900 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: 0.9452. Min Range: -0.9452

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1975638 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1980145 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1217983 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1897464 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1398754 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6904. Min Act: -0.0000

Data Index: 464865 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7233. Min Act: -0.0000

Data Index: 700216 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1511536 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1671871 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7673. Min Act: -0.0000

Data Index: 142355 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1421468 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6649. Min Act: -0.0000

Data Index: 840514 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1159652 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6647. Min Act: -0.0000

Data Index: 429219 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6536. Min Act: -0.0000

Data Index: 329584 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6158. Min Act: -0.0000

Data Index: 31704 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6142. Min Act: -0.0000

Data Index: 411260 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1603448 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6391. Min Act: -0.0000

Data Index: 638413 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6392. Min Act: -0.0000

Data Index: 469422 (The Pile)

Max Activating Token Index: 1010