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

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

Neuron 4880 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0397. Min Act: -0.0002

Data Index: 969548 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9751. Min Act: -0.0002

Data Index: 532860 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9801. Min Act: -0.0002

Data Index: 1257952 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9612. Min Act: -0.0002

Data Index: 1073540 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9741. Min Act: -0.0002

Data Index: 152854 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9598. Min Act: -0.0002

Data Index: 1072502 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9666. Min Act: -0.0002

Data Index: 943840 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9538. Min Act: -0.0002

Data Index: 60558 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9280. Min Act: -0.0002

Data Index: 254491 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9462. Min Act: -0.0002

Data Index: 968990 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9338. Min Act: -0.0002

Data Index: 41696 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9366. Min Act: -0.0002

Data Index: 1331010 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9383. Min Act: -0.0002

Data Index: 807255 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8894. Min Act: -0.0002

Data Index: 190699 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8963. Min Act: -0.0002

Data Index: 997422 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8828. Min Act: -0.0002

Data Index: 26220 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8850. Min Act: -0.0002

Data Index: 234166 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8768. Min Act: -0.0002

Data Index: 399119 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8600. Min Act: -0.0002

Data Index: 663006 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8850. Min Act: -0.0002

Data Index: 539602 (C4 (Web Text))

Max Activating Token Index: 809