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

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

Neuron 1023 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.7315. Min Act: -0.0000

Data Index: 1400978 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.7983. Min Act: -0.0000

Data Index: 1535044 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.4062. Min Act: -0.0000

Data Index: 683108 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.2663. Min Act: -0.0000

Data Index: 319516 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.2646. Min Act: -0.0000

Data Index: 195177 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1343759 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1610. Min Act: -0.0001

Data Index: 1393743 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1419132 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1494151 (Python Code)

Max Activating Token Index: 714

Text #9

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1620555 (Python Code)

Max Activating Token Index: 325

Text #10

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1480303 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1591. Min Act: -0.0000

Data Index: 477696 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.0773. Min Act: -0.0000

Data Index: 972062 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1398102 (Python Code)

Max Activating Token Index: 899

Text #14

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.0908. Min Act: -0.0000

Data Index: 539878 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1464883 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1477510 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1087405 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1104. Min Act: -0.0000

Data Index: 1159477 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.7983. Min Range: -1.7983

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1627174 (Python Code)

Max Activating Token Index: 692