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

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

Neuron 447 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1008. Min Range: -2.1008

Max Act: 2.1008. Min Act: -0.0000

Data Index: 614171 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.8805. Min Act: -0.0000

Data Index: 295217 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.6615. Min Act: -0.0000

Data Index: 508220 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.6449. Min Act: -0.0000

Data Index: 340220 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.6175. Min Act: -0.0000

Data Index: 648338 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.5227. Min Act: -0.0000

Data Index: 359543 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4961. Min Act: -0.0000

Data Index: 637028 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4808. Min Act: -0.0000

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4782. Min Act: -0.0000

Data Index: 55757 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4855. Min Act: -0.0000

Data Index: 810879 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.5457. Min Act: -0.0000

Data Index: 389378 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.5274. Min Act: -0.0000

Data Index: 492337 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1287701 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4046. Min Act: -0.0000

Data Index: 776633 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.4112. Min Act: -0.0000

Data Index: 578011 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.3617. Min Act: -0.0000

Data Index: 289099 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.2702. Min Act: -0.0000

Data Index: 161004 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.3427. Min Act: -0.0000

Data Index: 810267 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.3608. Min Act: -0.0000

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 2.1008. Min Range: -2.1008

Max Act: 1.2943. Min Act: -0.0000

Data Index: 480424 (C4 (Web Text))

Max Activating Token Index: 164