Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1425 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.8152. Min Act: -0.0000

Data Index: 1587168 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.8235. Min Act: -0.0000

Data Index: 883727 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.6779. Min Act: -0.0000

Data Index: 1894770 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.5645. Min Act: -0.0000

Data Index: 663996 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.3653. Min Act: -0.0000

Data Index: 239416 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.4607. Min Act: -0.0000

Data Index: 986043 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.4384. Min Act: -0.0000

Data Index: 1126893 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.1308. Min Act: -0.0000

Data Index: 929422 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 3.8235. Min Range: -3.8235

Max Act: 2.9084. Min Act: -0.0000

Data Index: 393013 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.1952. Min Act: -0.0000

Data Index: 299716 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.3085. Min Act: -0.0000

Data Index: 968772 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 3.8235. Min Range: -3.8235

Max Act: 2.6451. Min Act: -0.0000

Data Index: 435763 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.2314. Min Act: -0.0000

Data Index: 441218 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.2027. Min Act: -0.0000

Data Index: 137338 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 3.8235. Min Range: -3.8235

Max Act: 2.8102. Min Act: -0.0000

Data Index: 830184 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.1799. Min Act: -0.0000

Data Index: 1804084 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 3.8235. Min Range: -3.8235

Max Act: 2.7866. Min Act: -0.0000

Data Index: 455809 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.1959. Min Act: -0.0000

Data Index: 840051 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.1667. Min Act: -0.0000

Data Index: 52073 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 3.8235. Min Range: -3.8235

Max Act: 3.1612. Min Act: -0.0000

Data Index: 390176 (The Pile)

Max Activating Token Index: 748