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

Dataset: The Pile

Neuron 2319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1870496 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.8544. Min Act: -0.0000

Data Index: 614948 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1325120 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.6631. Min Act: -0.0000

Data Index: 725083 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.7405. Min Act: -0.0000

Data Index: 384213 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.5136. Min Act: -0.0000

Data Index: 413399 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.5961. Min Act: -0.0000

Data Index: 1995904 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1721465 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.6061. Min Act: -0.0000

Data Index: 979440 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1433832 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1186206 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1961275 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1799279 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.4489. Min Act: -0.0000

Data Index: 35672 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.3514. Min Act: -0.0000

Data Index: 720093 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1273659 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1213439 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.2519. Min Act: -0.0000

Data Index: 1573313 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.1940. Min Act: -0.0000

Data Index: 904437 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 1.9154. Min Range: -1.9154

Max Act: 1.2173. Min Act: -0.0000

Data Index: 926735 (The Pile)

Max Activating Token Index: 715