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

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

Neuron 397 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: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0003

Data Index: 460368 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0302. Min Act: -0.0003

Data Index: 896537 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0303. Min Act: -0.0003

Data Index: 936510 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0278. Min Act: -0.0003

Data Index: 929068 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1633435 (Python Code)

Max Activating Token Index: 120

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0278. Min Act: -0.0003

Data Index: 454653 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1639897 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1603727 (Python Code)

Max Activating Token Index: 758

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0277. Min Act: -0.0003

Data Index: 941089 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0283. Min Act: -0.0003

Data Index: 115097 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0255. Min Act: -0.0003

Data Index: 938709 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1003747 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1593077 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0289. Min Act: -0.0003

Data Index: 536278 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1067652 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1598620 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0265. Min Act: -0.0003

Data Index: 774283 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1529951 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0258. Min Act: -0.0003

Data Index: 514327 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1468289 (Python Code)

Max Activating Token Index: 425