Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5919 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.1674. Min Act: -0.0000

Data Index: 771343 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9932. Min Act: -0.0000

Data Index: 870001 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1341599 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9743. Min Act: 0.0000

Data Index: 1050203 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1204530 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9474. Min Act: -0.0000

Data Index: 301274 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9935. Min Act: -0.0000

Data Index: 709503 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8866. Min Act: 0.0000

Data Index: 841844 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8767. Min Act: -0.0000

Data Index: 344348 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8726. Min Act: -0.0000

Data Index: 967829 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8190. Min Act: -0.0000

Data Index: 527718 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8579. Min Act: -0.0000

Data Index: 836420 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8418. Min Act: -0.0000

Data Index: 30855 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8382. Min Act: -0.0000

Data Index: 283465 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7795. Min Act: 0.0000

Data Index: 1136926 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8181. Min Act: -0.0000

Data Index: 108932 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9311. Min Act: 0.0000

Data Index: 556742 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1351748 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7407. Min Act: -0.0000

Data Index: 59576 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7730. Min Act: -0.0000

Data Index: 17326 (C4 (Web Text))

Max Activating Token Index: 401