Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 429 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0920. Min Act: -0.0006

Data Index: 80062 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0006

Data Index: 1213824 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0890. Min Act: -0.0006

Data Index: 1207848 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0821. Min Act: -0.0006

Data Index: 582910 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0850. Min Act: -0.0006

Data Index: 486297 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0816. Min Act: -0.0006

Data Index: 1313367 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0746. Min Act: -0.0006

Data Index: 799916 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0788. Min Act: -0.0006

Data Index: 243440 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0785. Min Act: -0.0006

Data Index: 774248 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0772. Min Act: -0.0006

Data Index: 1326822 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0767. Min Act: -0.0006

Data Index: 1247486 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0766. Min Act: -0.0005

Data Index: 909054 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0728. Min Act: -0.0006

Data Index: 277197 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0757. Min Act: -0.0006

Data Index: 1157944 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0753. Min Act: -0.0006

Data Index: 417783 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0719. Min Act: -0.0006

Data Index: 384352 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0736. Min Act: -0.0006

Data Index: 235690 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0709. Min Act: -0.0006

Data Index: 280379 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0735. Min Act: -0.0006

Data Index: 437707 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0731. Min Act: -0.0006

Data Index: 334603 (C4 (Web Text))

Max Activating Token Index: 949