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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.8785. Min Act: -0.0000

Data Index: 1207913 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.6235. Min Act: -0.0000

Data Index: 370086 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.5941. Min Act: -0.0000

Data Index: 601541 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.4750. Min Act: -0.0000

Data Index: 682950 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.6089. Min Act: -0.0000

Data Index: 620512 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3817. Min Act: -0.0000

Data Index: 280951 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.2716. Min Act: -0.0000

Data Index: 425466 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.4968. Min Act: -0.0000

Data Index: 316059 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3973. Min Act: -0.0000

Data Index: 1333822 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1205895 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3673. Min Act: -0.0001

Data Index: 1231107 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3686. Min Act: -0.0000

Data Index: 452523 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3927. Min Act: -0.0000

Data Index: 103488 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3808. Min Act: -0.0000

Data Index: 505664 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.1959. Min Act: -0.0000

Data Index: 180261 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.3346. Min Act: -0.0000

Data Index: 1199179 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.2557. Min Act: -0.0000

Data Index: 835710 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1232219 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1075764 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 1.8785. Min Range: -1.8785

Max Act: 1.2778. Min Act: -0.0000

Data Index: 555574 (C4 (Web Text))

Max Activating Token Index: 145