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

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

Neuron 1917 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: 1.5984. Min Range: -1.5984

Max Act: 1.5984. Min Act: -0.0000

Data Index: 1523821 (Python Code)

Max Activating Token Index: 196

Text #1

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1648465 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1602740 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1075596 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1560586 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1016398 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.3571. Min Act: -0.0000

Data Index: 729182 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1536390 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1487674 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1463890 (Python Code)

Max Activating Token Index: 751

Text #10

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1555713 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1537714 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1637958 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1963. Min Act: 0.0001

Data Index: 874761 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1634950 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1408857 (Python Code)

Max Activating Token Index: 715

Text #16

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1807. Min Act: -0.0000

Data Index: 786909 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1448676 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1622546 (Python Code)

Max Activating Token Index: 181

Text #19

Max Range: 1.5984. Min Range: -1.5984

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1528165 (Python Code)

Max Activating Token Index: 76