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

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

Neuron 618 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.9239. Min Act: -0.0000

Data Index: 1392083 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.6929. Min Act: -0.0000

Data Index: 1596572 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.8936. Min Act: -0.0000

Data Index: 1436226 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.4114. Min Act: -0.0000

Data Index: 1427988 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.7514. Min Act: -0.0000

Data Index: 1646401 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3717. Min Act: -0.0000

Data Index: 1493987 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.5549. Min Act: -0.0000

Data Index: 1365164 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.4156. Min Act: -0.0000

Data Index: 1526123 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.4097. Min Act: -0.0000

Data Index: 1445999 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.5469. Min Act: -0.0000

Data Index: 1581856 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3534. Min Act: -0.0000

Data Index: 1435442 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.1218. Min Act: -0.0000

Data Index: 1591956 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 2.9239. Min Range: -2.9239

Max Act: 1.9722. Min Act: -0.0000

Data Index: 1550569 (Python Code)

Max Activating Token Index: 757

Text #13

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2841. Min Act: -0.0000

Data Index: 1640697 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2702. Min Act: -0.0000

Data Index: 1601108 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.1258. Min Act: -0.0000

Data Index: 1550644 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2743. Min Act: -0.0000

Data Index: 1572024 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2419. Min Act: -0.0000

Data Index: 1542674 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2414. Min Act: -0.0000

Data Index: 1645921 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2431. Min Act: -0.0000

Data Index: 1469689 (Python Code)

Max Activating Token Index: 313