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

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

Neuron 3032 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2223. Min Act: -0.0001

Data Index: 788662 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2169. Min Act: -0.0000

Data Index: 412955 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2075. Min Act: -0.0001

Data Index: 883668 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1887. Min Act: -0.0000

Data Index: 149501 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2008. Min Act: -0.0001

Data Index: 416350 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1941. Min Act: -0.0000

Data Index: 929027 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1242091 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1941. Min Act: -0.0000

Data Index: 376654 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1871. Min Act: -0.0000

Data Index: 637815 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1910. Min Act: -0.0000

Data Index: 176110 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1839. Min Act: -0.0000

Data Index: 361668 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1343470 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1798. Min Act: -0.0001

Data Index: 916921 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1781. Min Act: -0.0001

Data Index: 581724 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1846. Min Act: -0.0000

Data Index: 495818 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1660. Min Act: -0.0000

Data Index: 325434 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1759. Min Act: -0.0001

Data Index: 713742 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1028878 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1071326 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1830. Min Act: -0.0001

Data Index: 634131 (C4 (Web Text))

Max Activating Token Index: 257