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

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

Neuron 2867 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1580757 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1651253 (Python Code)

Max Activating Token Index: 362

Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1330. Min Act: -0.0001

Data Index: 506240 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1296. Min Act: -0.0001

Data Index: 317442 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1308. Min Act: -0.0001

Data Index: 133491 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1516315 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1346428 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1228. Min Act: -0.0001

Data Index: 240400 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1577918 (Python Code)

Max Activating Token Index: 466

Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1232. Min Act: -0.0001

Data Index: 452385 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1469501 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1563331 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1386122 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1370271 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1530104 (Python Code)

Max Activating Token Index: 635

Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1407812 (Python Code)

Max Activating Token Index: 949

Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1400223 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1362881 (Python Code)

Max Activating Token Index: 307

Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1379456 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1088506 (C4 (Web Text))

Max Activating Token Index: 116