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

Dataset: The Pile

Neuron 3300 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: 0.6948. Min Range: -0.6948

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1475454 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6641. Min Act: -0.0000

Data Index: 978722 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6298. Min Act: -0.0000

Data Index: 539426 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1156242 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6146. Min Act: -0.0000

Data Index: 970412 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5986. Min Act: -0.0000

Data Index: 780433 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1637686 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1651678 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5417. Min Act: -0.0000

Data Index: 33190 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5566. Min Act: -0.0000

Data Index: 769039 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1220158 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1734703 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5160. Min Act: -0.0000

Data Index: 906477 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1629504 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1650950 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5275. Min Act: -0.0000

Data Index: 555642 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1042568 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5411. Min Act: -0.0000

Data Index: 523849 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5321. Min Act: -0.0000

Data Index: 865941 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5288. Min Act: -0.0000

Data Index: 314237 (The Pile)

Max Activating Token Index: 355