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

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

Neuron 2318 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1537305 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1440349 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1438835 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1517080 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1536233 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1368646 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1577963 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1561119 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1518088 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1566684 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1514782 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1461957 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1469430 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1501821 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1463164 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1566934 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1496273 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1423033 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1616780 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1461449 (Python Code)

Max Activating Token Index: 762