Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3794 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1827861 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1157809 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1880557 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2092. Min Act: -0.0000

Data Index: 803931 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1028681 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1933878 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1614535 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1445. Min Act: -0.0000

Data Index: 705392 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1989561 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1400764 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1647338 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1932808 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1909492 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0437. Min Act: -0.0000

Data Index: 610845 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0294. Min Act: -0.0000

Data Index: 105754 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1510884 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1068. Min Act: -0.0000

Data Index: 467482 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0760. Min Act: -0.0000

Data Index: 740008 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0761. Min Act: -0.0000

Data Index: 331593 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0104. Min Act: -0.0000

Data Index: 559166 (The Pile)

Max Activating Token Index: 258