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

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

Neuron 3116 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.5662. Min Act: -0.0001

Data Index: 891417 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.4552. Min Act: -0.0001

Data Index: 790359 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.3002. Min Act: -0.0001

Data Index: 239870 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.4510. Min Act: -0.0001

Data Index: 847793 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2396. Min Act: -0.0001

Data Index: 703100 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.2865. Min Act: -0.0001

Data Index: 772782 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.3013. Min Act: -0.0001

Data Index: 145758 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1665. Min Act: -0.0001

Data Index: 892951 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1564. Min Act: -0.0001

Data Index: 296087 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1737. Min Act: -0.0001

Data Index: 38708 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1255. Min Act: -0.0001

Data Index: 246234 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1284. Min Act: -0.0001

Data Index: 1217255 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0858. Min Act: -0.0001

Data Index: 1222551 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.1109. Min Act: -0.0001

Data Index: 779813 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.9646. Min Act: -0.0001

Data Index: 1129830 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0959. Min Act: -0.0001

Data Index: 1080511 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.8872. Min Act: -0.0001

Data Index: 327915 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1577173 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 1.5662. Min Range: -1.5662

Max Act: 1.0196. Min Act: -0.0001

Data Index: 1149115 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.5662. Min Range: -1.5662

Max Act: 0.9798. Min Act: -0.0001

Data Index: 311296 (C4 (Web Text))

Max Activating Token Index: 206