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

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

Neuron 3696 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: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0001

Data Index: 714023 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1293. Min Act: -0.0000

Data Index: 708747 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1076. Min Act: -0.0000

Data Index: 98590 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1248630 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1025. Min Act: -0.0000

Data Index: 172561 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1272607 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0957. Min Act: -0.0001

Data Index: 327926 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0915. Min Act: -0.0000

Data Index: 593765 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0907. Min Act: -0.0000

Data Index: 132820 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0957. Min Act: -0.0001

Data Index: 397119 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0907. Min Act: -0.0000

Data Index: 700946 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0914. Min Act: -0.0001

Data Index: 843636 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1114338 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1107308 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0872. Min Act: -0.0000

Data Index: 576010 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0900. Min Act: -0.0000

Data Index: 216002 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0935. Min Act: -0.0001

Data Index: 641935 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1073711 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0879. Min Act: -0.0000

Data Index: 64819 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0813. Min Act: -0.0001

Data Index: 525479 (C4 (Web Text))

Max Activating Token Index: 917