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

Dataset: The Pile

Neuron 1531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1682709 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2495. Min Act: -0.0000

Data Index: 877730 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1086289 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1210179 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1707177 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2067. Min Act: -0.0000

Data Index: 365486 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1489859 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2027. Min Act: -0.0000

Data Index: 188234 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1964. Min Act: -0.0000

Data Index: 257146 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1693863 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1805931 (The Pile)

Max Activating Token Index: 642

Text #11

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1637222 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1869. Min Act: -0.0000

Data Index: 292686 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1233363 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1165305 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1779. Min Act: -0.0000

Data Index: 736853 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1894856 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1706392 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1274181 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 0.2692. Min Range: -0.2692

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1372166 (The Pile)

Max Activating Token Index: 296