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

Dataset: The Pile

Neuron 3509 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: 3.1036. Min Range: -3.1036

Max Act: 3.1036. Min Act: -0.0000

Data Index: 1296954 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 3.1036. Min Range: -3.1036

Max Act: 2.7963. Min Act: -0.0000

Data Index: 1095499 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 3.1036. Min Range: -3.1036

Max Act: 2.6159. Min Act: -0.0000

Data Index: 861455 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 3.1036. Min Range: -3.1036

Max Act: 2.0722. Min Act: -0.0000

Data Index: 365707 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 3.1036. Min Range: -3.1036

Max Act: 2.0739. Min Act: -0.0000

Data Index: 598136 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 3.1036. Min Range: -3.1036

Max Act: 2.2314. Min Act: -0.0000

Data Index: 1052986 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1866504 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1124837 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1747839 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.8258. Min Act: -0.0000

Data Index: 1794862 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1079555 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.6107. Min Act: -0.0000

Data Index: 824850 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.7047. Min Act: -0.0000

Data Index: 583948 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.5354. Min Act: -0.0000

Data Index: 338927 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.4034. Min Act: -0.0000

Data Index: 1919148 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1598139 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.3244. Min Act: -0.0000

Data Index: 330144 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1039342 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.3901. Min Act: -0.0000

Data Index: 617701 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 3.1036. Min Range: -3.1036

Max Act: 1.2820. Min Act: -0.0000

Data Index: 632616 (The Pile)

Max Activating Token Index: 312