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

Dataset: The Pile

Neuron 2467 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4871. Min Act: -0.0000

Data Index: 432440 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3907. Min Act: -0.0000

Data Index: 800179 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4389. Min Act: -0.0000

Data Index: 299157 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1782048 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3735. Min Act: -0.0000

Data Index: 273704 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3843. Min Act: -0.0000

Data Index: 201877 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3743. Min Act: -0.0000

Data Index: 731639 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3795. Min Act: -0.0000

Data Index: 821608 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1822065 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1821525 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1756680 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1977743 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1473599 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3460. Min Act: -0.0000

Data Index: 243732 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3204. Min Act: -0.0000

Data Index: 23465 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1294832 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1734632 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3418. Min Act: -0.0000

Data Index: 453805 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3503. Min Act: -0.0000

Data Index: 617754 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3258. Min Act: -0.0000

Data Index: 738333 (The Pile)

Max Activating Token Index: 327