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

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

Neuron 767 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3865. Min Act: -0.0000

Data Index: 319192 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3724. Min Act: -0.0000

Data Index: 489220 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3531. Min Act: -0.0000

Data Index: 618495 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1210737 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3151. Min Act: -0.0000

Data Index: 603357 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2982. Min Act: -0.0000

Data Index: 397152 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1285190 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3090. Min Act: -0.0000

Data Index: 935361 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2785. Min Act: -0.0000

Data Index: 445849 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2873. Min Act: -0.0000

Data Index: 488512 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2938. Min Act: -0.0000

Data Index: 453128 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2937. Min Act: -0.0000

Data Index: 34071 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2742. Min Act: -0.0000

Data Index: 563135 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2818. Min Act: -0.0000

Data Index: 282219 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1077392 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2609. Min Act: -0.0000

Data Index: 125189 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1261636 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2873. Min Act: -0.0000

Data Index: 50900 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1004293 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2599. Min Act: -0.0000

Data Index: 296643 (C4 (Web Text))

Max Activating Token Index: 174