Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1846 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4888. Min Act: -0.0001

Data Index: 187866 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3996. Min Act: -0.0001

Data Index: 291206 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1223518 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1290779 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1025254 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2891. Min Act: -0.0001

Data Index: 913797 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2978. Min Act: -0.0001

Data Index: 344279 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2845. Min Act: -0.0001

Data Index: 145724 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1267658 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3086. Min Act: -0.0001

Data Index: 945854 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2852. Min Act: -0.0001

Data Index: 168086 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2749. Min Act: -0.0001

Data Index: 1086079 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1076431 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1200746 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2813. Min Act: -0.0001

Data Index: 63423 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2706. Min Act: -0.0001

Data Index: 899071 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2669. Min Act: -0.0001

Data Index: 921402 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2659. Min Act: -0.0001

Data Index: 211191 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2473. Min Act: -0.0001

Data Index: 940020 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2841. Min Act: -0.0001

Data Index: 601414 (C4 (Web Text))

Max Activating Token Index: 632