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

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

Neuron 1726 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: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1315441 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1061654 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1349304 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0740. Min Act: -0.0002

Data Index: 809410 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0729. Min Act: -0.0002

Data Index: 13531 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0711. Min Act: -0.0002

Data Index: 187966 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0735. Min Act: -0.0003

Data Index: 780704 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0729. Min Act: -0.0002

Data Index: 128629 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0710. Min Act: -0.0002

Data Index: 778025 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1295385 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0701. Min Act: -0.0002

Data Index: 164916 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1017072 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0682. Min Act: -0.0002

Data Index: 329671 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0691. Min Act: -0.0002

Data Index: 280920 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0681. Min Act: -0.0002

Data Index: 712387 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1165586 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0684. Min Act: -0.0002

Data Index: 421852 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0667. Min Act: -0.0002

Data Index: 842839 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0659. Min Act: -0.0002

Data Index: 925630 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0669. Min Act: -0.0002

Data Index: 436744 (C4 (Web Text))

Max Activating Token Index: 772