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

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

Neuron 578 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1487801 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1625308 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.2700. Min Act: -0.0000

Data Index: 942652 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1511236 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.1680. Min Act: -0.0000

Data Index: 468773 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1405882 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1039317 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0255. Min Act: -0.0000

Data Index: 1531044 (Python Code)

Max Activating Token Index: 363

Text #8

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1145140 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1445139 (Python Code)

Max Activating Token Index: 558

Text #10

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1490550 (Python Code)

Max Activating Token Index: 612

Text #11

Max Range: 1.2700. Min Range: -1.2700

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1514315 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1453835 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 1.2700. Min Range: -1.2700

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1439558 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.2700. Min Range: -1.2700

Max Act: 0.9581. Min Act: -0.0000

Data Index: 841839 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.2700. Min Range: -1.2700

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1476747 (Python Code)

Max Activating Token Index: 427

Text #17

Max Range: 1.2700. Min Range: -1.2700

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1043944 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.2700. Min Range: -1.2700

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1563886 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 1.2700. Min Range: -1.2700

Max Act: 0.8831. Min Act: -0.0000

Data Index: 386605 (C4 (Web Text))

Max Activating Token Index: 367