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

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

Neuron 4044 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: 0.8674. Min Range: -0.8674

Max Act: 0.8674. Min Act: -0.0000

Data Index: 8874 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8563. Min Act: -0.0000

Data Index: 255283 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8555. Min Act: -0.0000

Data Index: 54690 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8281. Min Act: -0.0000

Data Index: 232712 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7504. Min Act: -0.0000

Data Index: 303848 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8158. Min Act: -0.0000

Data Index: 148592 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7874. Min Act: -0.0000

Data Index: 594747 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1118563 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8084. Min Act: -0.0000

Data Index: 126696 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7224. Min Act: -0.0000

Data Index: 521840 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7677. Min Act: -0.0000

Data Index: 493967 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7879. Min Act: -0.0000

Data Index: 616872 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7404. Min Act: -0.0000

Data Index: 211048 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7730. Min Act: -0.0000

Data Index: 183982 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7126. Min Act: -0.0000

Data Index: 804611 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7036. Min Act: -0.0000

Data Index: 235261 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6711. Min Act: -0.0000

Data Index: 450489 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1035590 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7507. Min Act: -0.0000

Data Index: 531013 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6934. Min Act: -0.0000

Data Index: 361047 (C4 (Web Text))

Max Activating Token Index: 788