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

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

Neuron 5980 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5214. Min Range: -2.5214

Max Act: 2.5214. Min Act: -0.0000

Data Index: 642729 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 2.5214. Min Range: -2.5214

Max Act: 2.2506. Min Act: -0.0000

Data Index: 1161315 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 2.5214. Min Range: -2.5214

Max Act: 2.1188. Min Act: -0.0000

Data Index: 1490664 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 2.5214. Min Range: -2.5214

Max Act: 2.1706. Min Act: -0.0000

Data Index: 1518669 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.8565. Min Act: -0.0000

Data Index: 306121 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.8674. Min Act: -0.0000

Data Index: 1622214 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.6641. Min Act: -0.0000

Data Index: 179098 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.7284. Min Act: -0.0000

Data Index: 1539151 (Python Code)

Max Activating Token Index: 292

Text #8

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.7223. Min Act: -0.0000

Data Index: 52048 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.7110. Min Act: -0.0000

Data Index: 1428773 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1528559 (Python Code)

Max Activating Token Index: 692

Text #11

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.5838. Min Act: -0.0000

Data Index: 1554724 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1495123 (Python Code)

Max Activating Token Index: 277

Text #13

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.6577. Min Act: -0.0000

Data Index: 1536936 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1557966 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1608575 (Python Code)

Max Activating Token Index: 598

Text #16

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1579745 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1638902 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.5685. Min Act: -0.0000

Data Index: 1618016 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 2.5214. Min Range: -2.5214

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1546584 (Python Code)

Max Activating Token Index: 169