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

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

Neuron 2083 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2801. Min Act: -0.0000

Data Index: 302574 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1255841 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2644. Min Act: 0.0000

Data Index: 290453 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2530. Min Act: -0.0000

Data Index: 605129 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2702. Min Act: -0.0000

Data Index: 370454 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2479. Min Act: -0.0000

Data Index: 163249 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2443. Min Act: -0.0000

Data Index: 936148 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2425. Min Act: -0.0000

Data Index: 476849 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1189734 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2401. Min Act: -0.0000

Data Index: 684203 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2281. Min Act: -0.0000

Data Index: 720124 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2440. Min Act: -0.0000

Data Index: 865167 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2389. Min Act: -0.0000

Data Index: 931645 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1069420 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2257. Min Act: -0.0000

Data Index: 335162 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1239053 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2141. Min Act: -0.0000

Data Index: 252687 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2289. Min Act: -0.0000

Data Index: 429539 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1015579 (C4 (Web Text))

Max Activating Token Index: 465