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

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

Neuron 1652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: -0.0000

Data Index: 273253 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1561. Min Act: -0.0000

Data Index: 703404 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1443. Min Act: -0.0000

Data Index: 520008 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1468. Min Act: -0.0000

Data Index: 41733 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1341. Min Act: -0.0000

Data Index: 752449 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1400. Min Act: -0.0000

Data Index: 590332 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1504. Min Act: -0.0000

Data Index: 148434 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1374. Min Act: -0.0000

Data Index: 201894 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1293. Min Act: -0.0000

Data Index: 286163 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1132480 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1410. Min Act: -0.0000

Data Index: 622017 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1270. Min Act: -0.0000

Data Index: 392064 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1256. Min Act: -0.0000

Data Index: 508521 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1254. Min Act: -0.0000

Data Index: 953562 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1224963 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1235. Min Act: -0.0000

Data Index: 700952 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1365707 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1249. Min Act: -0.0000

Data Index: 133244 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1162. Min Act: -0.0000

Data Index: 482214 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1200. Min Act: -0.0000

Data Index: 146075 (C4 (Web Text))

Max Activating Token Index: 82