Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2939. Min Act: -0.0000

Data Index: 155456 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2922. Min Act: -0.0001

Data Index: 313962 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1599565 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2433. Min Act: -0.0000

Data Index: 486795 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2143. Min Act: -0.0001

Data Index: 452451 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2324. Min Act: -0.0000

Data Index: 649788 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1557193 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2216. Min Act: -0.0001

Data Index: 718541 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2172. Min Act: -0.0000

Data Index: 294388 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1488856 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2092. Min Act: -0.0001

Data Index: 658215 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1997. Min Act: -0.0000

Data Index: 139082 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1006443 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1837. Min Act: -0.0000

Data Index: 128231 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1765. Min Act: -0.0001

Data Index: 973271 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1883. Min Act: -0.0000

Data Index: 218001 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1810. Min Act: -0.0001

Data Index: 995403 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1807. Min Act: -0.0000

Data Index: 187925 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1313726 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1693. Min Act: -0.0000

Data Index: 435225 (C4 (Web Text))

Max Activating Token Index: 375