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

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

Neuron 721 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: 0.2576. Min Range: -0.2576

Max Act: 0.2576. Min Act: -0.0000

Data Index: 299531 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2459. Min Act: -0.0000

Data Index: 12392 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2518. Min Act: -0.0000

Data Index: 934615 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2439. Min Act: -0.0000

Data Index: 717030 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1048543 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2301. Min Act: -0.0000

Data Index: 520089 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2289. Min Act: -0.0000

Data Index: 77875 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1358534 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2316. Min Act: -0.0000

Data Index: 170356 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2260. Min Act: -0.0000

Data Index: 35749 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2126. Min Act: -0.0000

Data Index: 767264 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2146. Min Act: -0.0000

Data Index: 872745 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1275034 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1272137 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1932. Min Act: -0.0000

Data Index: 369989 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1081545 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2041. Min Act: -0.0000

Data Index: 955960 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1228151 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1235778 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1901. Min Act: -0.0000

Data Index: 896700 (C4 (Web Text))

Max Activating Token Index: 56