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

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

Neuron 1529 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: 0.2248. Min Range: -0.2248

Max Act: 0.2248. Min Act: -0.0001

Data Index: 732948 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1337212 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.2163. Min Act: -0.0000

Data Index: 378267 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.2002. Min Act: -0.0001

Data Index: 555057 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.2066. Min Act: -0.0001

Data Index: 156868 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.2026. Min Act: -0.0000

Data Index: 598778 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1827. Min Act: -0.0001

Data Index: 977555 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1842. Min Act: -0.0000

Data Index: 663739 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1816. Min Act: -0.0001

Data Index: 800407 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1919. Min Act: -0.0000

Data Index: 61902 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1346556 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1674. Min Act: -0.0001

Data Index: 849615 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1788. Min Act: -0.0000

Data Index: 885824 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1663. Min Act: -0.0000

Data Index: 829935 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1166792 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1025552 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1773. Min Act: -0.0001

Data Index: 201625 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1719. Min Act: -0.0001

Data Index: 674906 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1767. Min Act: -0.0001

Data Index: 375067 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.2248. Min Range: -0.2248

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1238652 (C4 (Web Text))

Max Activating Token Index: 506