Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0002

Data Index: 848400 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0341. Min Act: -0.0002

Data Index: 299876 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0315. Min Act: -0.0002

Data Index: 503708 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0293. Min Act: -0.0002

Data Index: 425751 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0287. Min Act: -0.0002

Data Index: 385555 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0294. Min Act: -0.0002

Data Index: 978870 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1485548 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1641447 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1646330 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1526311 (Python Code)

Max Activating Token Index: 745

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1247323 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1428540 (Python Code)

Max Activating Token Index: 490

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1591562 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0249. Min Act: -0.0002

Data Index: 889422 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0252. Min Act: -0.0002

Data Index: 785238 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1589468 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1630361 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0245. Min Act: -0.0002

Data Index: 630778 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1484587 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0226. Min Act: -0.0002

Data Index: 613525 (C4 (Web Text))

Max Activating Token Index: 284