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

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

Neuron 1326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1429258 (Python Code)

Max Activating Token Index: 715

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1500. Min Act: -0.0001

Data Index: 1490027 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1622380 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1511781 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0881. Min Act: -0.0000

Data Index: 556570 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1379573 (Python Code)

Max Activating Token Index: 890

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1558294 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0823. Min Act: -0.0000

Data Index: 92526 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1623793 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1621635 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1417375 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0752. Min Act: -0.0000

Data Index: 852183 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1552929 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1411237 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0759. Min Act: -0.0000

Data Index: 107668 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0762. Min Act: -0.0000

Data Index: 231282 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1617184 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1621852 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1394765 (Python Code)

Max Activating Token Index: 950

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1433373 (Python Code)

Max Activating Token Index: 632