Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2311 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1649439 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1236828 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: -0.0003

Data Index: 81378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0276. Min Act: -0.0004

Data Index: 1371637 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1650281 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1444459 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0263. Min Act: -0.0003

Data Index: 985556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1603957 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1434519 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1390039 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0243. Min Act: -0.0003

Data Index: 624262 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1401739 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1199332 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1053668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0209. Min Act: -0.0004

Data Index: 258379 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1037616 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1644182 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1512190 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1369725 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1367471 (Python Code)

Max Activating Token Index: 15