Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2057 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8394. Min Act: -0.0000

Data Index: 749363 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7442. Min Act: -0.0000

Data Index: 555947 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1201505 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7535. Min Act: -0.0000

Data Index: 326664 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7248. Min Act: 0.0000

Data Index: 1202103 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6881. Min Act: -0.0000

Data Index: 569908 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6577. Min Act: -0.0000

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1295319 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6456. Min Act: -0.0000

Data Index: 847032 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6142. Min Act: 0.0000

Data Index: 769428 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1209224 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1551078 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6024. Min Act: -0.0000

Data Index: 954924 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6243. Min Act: -0.0000

Data Index: 551914 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6247. Min Act: 0.0000

Data Index: 330970 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6405. Min Act: -0.0000

Data Index: 50712 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6233. Min Act: -0.0000

Data Index: 667221 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6393. Min Act: -0.0000

Data Index: 255194 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6222. Min Act: 0.0000

Data Index: 17898 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5973. Min Act: -0.0000

Data Index: 242840 (C4 (Web Text))

Max Activating Token Index: 1017