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

Dataset: The Pile

Neuron 406 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: 0.7884. Min Range: -0.7884

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1914611 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1509233 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1695867 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6063. Min Act: -0.0000

Data Index: 210155 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1613610 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1434443 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1941818 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1707862 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1415393 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1597757 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5644. Min Act: -0.0000

Data Index: 63947 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5252. Min Act: -0.0000

Data Index: 384588 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1917096 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5314. Min Act: -0.0000

Data Index: 934030 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5263. Min Act: -0.0000

Data Index: 876417 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5277. Min Act: -0.0000

Data Index: 478216 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1080305 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1400389 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.4598. Min Act: -0.0000

Data Index: 22232 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.4543. Min Act: -0.0000

Data Index: 302530 (The Pile)

Max Activating Token Index: 585