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

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

Neuron 1415 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0003

Data Index: 495585 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0327. Min Act: -0.0003

Data Index: 732830 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1361453 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0290. Min Act: -0.0003

Data Index: 594111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0272. Min Act: -0.0003

Data Index: 740747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1206983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0284. Min Act: -0.0003

Data Index: 603608 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0283. Min Act: -0.0003

Data Index: 844314 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0309. Min Act: -0.0003

Data Index: 733354 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0264. Min Act: -0.0003

Data Index: 520915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1270668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0234. Min Act: -0.0003

Data Index: 15402 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1189309 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0235. Min Act: -0.0003

Data Index: 236931 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0262. Min Act: -0.0003

Data Index: 778787 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0258. Min Act: -0.0003

Data Index: 265376 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1027827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1165552 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0270. Min Act: -0.0003

Data Index: 289896 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1117035 (C4 (Web Text))

Max Activating Token Index: 197