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

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

Neuron 4461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1297878 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0002

Data Index: 324866 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0845. Min Act: -0.0002

Data Index: 938351 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0722. Min Act: -0.0002

Data Index: 680838 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0735. Min Act: -0.0002

Data Index: 50512 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0820. Min Act: -0.0002

Data Index: 860941 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0769. Min Act: -0.0002

Data Index: 489064 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0779. Min Act: -0.0002

Data Index: 272176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1235476 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1018013 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0782. Min Act: -0.0002

Data Index: 813457 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0748. Min Act: -0.0002

Data Index: 100259 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0659. Min Act: -0.0002

Data Index: 547197 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0732. Min Act: -0.0002

Data Index: 68314 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0701. Min Act: -0.0002

Data Index: 580833 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0690. Min Act: -0.0002

Data Index: 993337 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0616. Min Act: -0.0002

Data Index: 322045 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0674. Min Act: -0.0002

Data Index: 571526 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1015222 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0630. Min Act: -0.0002

Data Index: 990061 (C4 (Web Text))

Max Activating Token Index: 285