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

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

Neuron 2091 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1019118 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6559. Min Act: -0.0000

Data Index: 635735 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4457. Min Act: -0.0000

Data Index: 2624 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1304559 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1089098 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3782. Min Act: -0.0000

Data Index: 377019 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3978. Min Act: -0.0000

Data Index: 432370 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3919. Min Act: -0.0000

Data Index: 31340 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3697. Min Act: -0.0000

Data Index: 896127 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1067815 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1106768 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3391. Min Act: -0.0000

Data Index: 593200 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3577. Min Act: -0.0000

Data Index: 406685 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1077494 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3556. Min Act: -0.0000

Data Index: 182957 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3412. Min Act: -0.0000

Data Index: 104885 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3519. Min Act: -0.0000

Data Index: 294604 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3284. Min Act: -0.0000

Data Index: 350717 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1095143 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3380. Min Act: -0.0000

Data Index: 178963 (C4 (Web Text))

Max Activating Token Index: 752