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

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

Neuron 5067 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2334. Min Act: -0.0002

Data Index: 954936 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2362. Min Act: -0.0002

Data Index: 886846 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1279363 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2342. Min Act: -0.0002

Data Index: 136838 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2322. Min Act: -0.0002

Data Index: 466815 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2329. Min Act: -0.0002

Data Index: 1245901 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2300. Min Act: -0.0002

Data Index: 874544 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2312. Min Act: -0.0002

Data Index: 92462 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2274. Min Act: -0.0002

Data Index: 866694 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2256. Min Act: -0.0002

Data Index: 671143 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2259. Min Act: -0.0002

Data Index: 497820 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2282. Min Act: -0.0002

Data Index: 357433 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2204. Min Act: -0.0002

Data Index: 506866 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2240. Min Act: -0.0002

Data Index: 713273 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2270. Min Act: -0.0002

Data Index: 674392 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2189. Min Act: -0.0002

Data Index: 1358738 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2206. Min Act: -0.0002

Data Index: 990147 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2242. Min Act: -0.0002

Data Index: 473203 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2228. Min Act: -0.0002

Data Index: 89110 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2171. Min Act: -0.0002

Data Index: 665333 (C4 (Web Text))

Max Activating Token Index: 724