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

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

Neuron 954 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.5258. Min Act: -0.0000

Data Index: 746864 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4384. Min Act: -0.0000

Data Index: 398808 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4367. Min Act: -0.0000

Data Index: 75322 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4152. Min Act: -0.0000

Data Index: 228451 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4125. Min Act: -0.0000

Data Index: 560326 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3806. Min Act: -0.0000

Data Index: 491991 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3804. Min Act: -0.0000

Data Index: 183873 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3940. Min Act: -0.0000

Data Index: 917799 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3544. Min Act: -0.0000

Data Index: 763953 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3643. Min Act: -0.0000

Data Index: 724433 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3559. Min Act: -0.0000

Data Index: 67941 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1251077 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1091563 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1055754 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.2757. Min Act: -0.0000

Data Index: 14466 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1191985 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1068652 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3178. Min Act: -0.0000

Data Index: 675801 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3006. Min Act: -0.0000

Data Index: 51888 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.2976. Min Act: -0.0000

Data Index: 143205 (C4 (Web Text))

Max Activating Token Index: 297