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

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

Neuron 1247 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7719. Min Act: -0.0001

Data Index: 1065571 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7136. Min Act: -0.0001

Data Index: 147200 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7200. Min Act: -0.0001

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6710. Min Act: -0.0001

Data Index: 768670 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.7081. Min Act: -0.0001

Data Index: 48066 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6639. Min Act: -0.0001

Data Index: 163501 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1196127 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6830. Min Act: -0.0001

Data Index: 658242 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6319. Min Act: -0.0001

Data Index: 30403 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6437. Min Act: -0.0001

Data Index: 396661 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6627. Min Act: -0.0001

Data Index: 942159 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6579. Min Act: -0.0001

Data Index: 334116 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6808. Min Act: -0.0001

Data Index: 391905 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6374. Min Act: -0.0001

Data Index: 386235 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6475. Min Act: -0.0001

Data Index: 94537 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6282. Min Act: -0.0001

Data Index: 505421 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6462. Min Act: -0.0001

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6283. Min Act: -0.0001

Data Index: 891331 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6209. Min Act: -0.0001

Data Index: 175330 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.7719. Min Range: -0.7719

Max Act: 0.6234. Min Act: -0.0001

Data Index: 697375 (C4 (Web Text))

Max Activating Token Index: 332