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

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

Neuron 3452 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: 0.2499. Min Range: -0.2499

Max Act: 0.2382. Min Act: -0.0000

Data Index: 954829 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2499. Min Act: -0.0000

Data Index: 213559 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2174. Min Act: -0.0001

Data Index: 823334 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2269. Min Act: -0.0000

Data Index: 121786 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2287. Min Act: -0.0000

Data Index: 708326 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1138659 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2060. Min Act: -0.0000

Data Index: 349868 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1879. Min Act: -0.0000

Data Index: 661020 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1225087 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2141. Min Act: -0.0000

Data Index: 181676 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1222251 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1758. Min Act: -0.0001

Data Index: 554648 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1801. Min Act: -0.0001

Data Index: 796348 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1932. Min Act: -0.0000

Data Index: 784310 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1303888 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1805. Min Act: -0.0001

Data Index: 462935 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1866. Min Act: -0.0000

Data Index: 168223 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1860. Min Act: -0.0000

Data Index: 843634 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1712. Min Act: -0.0001

Data Index: 749383 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1271945 (C4 (Web Text))

Max Activating Token Index: 762