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

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

Neuron 6009 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1389582 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1574533 (Python Code)

Max Activating Token Index: 575

Text #2

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1479559 (Python Code)

Max Activating Token Index: 507

Text #3

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1203087 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1449275 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1522476 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1456189 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2083. Min Act: -0.0000

Data Index: 179015 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1112990 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1277483 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1432713 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2029. Min Act: -0.0000

Data Index: 855391 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1599414 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1578338 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.1933. Min Act: -0.0000

Data Index: 393699 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1383956 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1394134 (Python Code)

Max Activating Token Index: 602

Text #17

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1510210 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1511294 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.2606. Min Range: -0.2606

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1484401 (Python Code)

Max Activating Token Index: 332