Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1846 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0413. Min Act: -0.0004

Data Index: 732945 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0004

Data Index: 346677 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0406. Min Act: -0.0004

Data Index: 1305681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1145949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0339. Min Act: -0.0004

Data Index: 858337 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0336. Min Act: -0.0004

Data Index: 627697 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0316. Min Act: -0.0004

Data Index: 113851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0256. Min Act: -0.0004

Data Index: 739524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1148602 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1306353 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0267. Min Act: -0.0004

Data Index: 1150468 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0248. Min Act: -0.0004

Data Index: 820731 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0327. Min Act: -0.0004

Data Index: 289487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0293. Min Act: -0.0004

Data Index: 425110 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0338. Min Act: -0.0004

Data Index: 769453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1025084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0345. Min Act: -0.0004

Data Index: 25403 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0266. Min Act: -0.0004

Data Index: 770789 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1599419 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0322. Min Act: -0.0004

Data Index: 88248 (C4 (Web Text))

Max Activating Token Index: 1023