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

Dataset: The Pile

Neuron 3280 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.6232. Min Act: -0.0000

Data Index: 1479557 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.2637. Min Act: -0.0000

Data Index: 267503 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1427525 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.2160. Min Act: -0.0000

Data Index: 384211 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9125. Min Act: -0.0000

Data Index: 135165 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0820. Min Act: -0.0000

Data Index: 1629962 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1072691 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1002132 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1241323 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1597251 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.1596. Min Act: -0.0000

Data Index: 353991 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9742. Min Act: -0.0000

Data Index: 342460 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1077712 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1497988 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1921583 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.8849. Min Act: -0.0000

Data Index: 654114 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.8916. Min Act: -0.0000

Data Index: 577956 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1594641 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.8829. Min Act: -0.0000

Data Index: 430293 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.8735. Min Act: -0.0000

Data Index: 399191 (The Pile)

Max Activating Token Index: 663