Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 945 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3811. Min Act: -0.0000

Data Index: 913661 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3782. Min Act: -0.0000

Data Index: 445863 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3964. Min Act: -0.0000

Data Index: 912766 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3362. Min Act: -0.0000

Data Index: 82763 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3328. Min Act: -0.0000

Data Index: 402213 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3408. Min Act: -0.0000

Data Index: 583137 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1397260 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3063. Min Act: -0.0000

Data Index: 358463 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3192. Min Act: -0.0000

Data Index: 839841 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2787. Min Act: -0.0000

Data Index: 822357 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1492097 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2850. Min Act: -0.0000

Data Index: 476244 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2974. Min Act: -0.0000

Data Index: 988682 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1229538 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2925. Min Act: -0.0000

Data Index: 225346 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3015. Min Act: -0.0000

Data Index: 331065 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1175145 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2977. Min Act: -0.0000

Data Index: 416690 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2893. Min Act: -0.0000

Data Index: 140300 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2599. Min Act: -0.0000

Data Index: 918160 (C4 (Web Text))

Max Activating Token Index: 406