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

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

Neuron 608 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: 0.3666. Min Range: -0.3666

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1080796 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1341589 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.3004. Min Act: -0.0000

Data Index: 431073 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2919. Min Act: -0.0000

Data Index: 519023 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2758. Min Act: -0.0000

Data Index: 812308 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1099615 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2779. Min Act: -0.0000

Data Index: 109169 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2737. Min Act: -0.0000

Data Index: 234948 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2852. Min Act: -0.0000

Data Index: 924126 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2661. Min Act: -0.0000

Data Index: 746919 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1229476 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2703. Min Act: -0.0000

Data Index: 319048 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1206020 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1301725 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2740. Min Act: -0.0000

Data Index: 732905 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2631. Min Act: -0.0000

Data Index: 548176 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2411. Min Act: -0.0000

Data Index: 841163 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1244190 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1192788 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.3666. Min Range: -0.3666

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1062598 (C4 (Web Text))

Max Activating Token Index: 477