Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.9827. Min Act: -0.0000

Data Index: 482304 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.8032. Min Act: -0.0001

Data Index: 316537 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.5536. Min Act: -0.0001

Data Index: 587185 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.6203. Min Act: -0.0000

Data Index: 431572 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.5377. Min Act: -0.0000

Data Index: 1337662 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1116589 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.3631. Min Act: -0.0000

Data Index: 555488 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.2527. Min Act: -0.0001

Data Index: 1260275 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1112015 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.2922. Min Act: -0.0000

Data Index: 704003 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.4617. Min Act: -0.0001

Data Index: 748838 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1202523 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.2486. Min Act: -0.0000

Data Index: 915526 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.2283. Min Act: -0.0000

Data Index: 731004 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.2710. Min Act: -0.0000

Data Index: 192708 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.3007. Min Act: -0.0000

Data Index: 7868 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.3322. Min Act: -0.0000

Data Index: 979264 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1157773 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.0908. Min Act: -0.0001

Data Index: 963511 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.1615. Min Act: -0.0000

Data Index: 366279 (C4 (Web Text))

Max Activating Token Index: 271