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

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

Neuron 4906 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: 2.8121. Min Range: -2.8121

Max Act: 2.6375. Min Act: -0.0000

Data Index: 1487292 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.7119. Min Act: -0.0000

Data Index: 1540527 (Python Code)

Max Activating Token Index: 384

Text #2

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.8121. Min Act: -0.0000

Data Index: 1632990 (Python Code)

Max Activating Token Index: 1010

Text #3

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.3932. Min Act: -0.0000

Data Index: 1626876 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.3869. Min Act: -0.0000

Data Index: 1497199 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.5060. Min Act: -0.0000

Data Index: 1364682 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.4797. Min Act: -0.0000

Data Index: 1477341 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.5939. Min Act: -0.0000

Data Index: 1403618 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.3639. Min Act: -0.0000

Data Index: 1397636 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.3155. Min Act: -0.0000

Data Index: 1471084 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.4074. Min Act: -0.0000

Data Index: 1514672 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.3828. Min Act: -0.0000

Data Index: 1583416 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.3619. Min Act: -0.0000

Data Index: 1411618 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1493684 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.0837. Min Act: -0.0000

Data Index: 1455062 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.0868. Min Act: -0.0000

Data Index: 1526359 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1620801 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.1184. Min Act: -0.0000

Data Index: 1568560 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 2.8121. Min Range: -2.8121

Max Act: 1.9991. Min Act: -0.0000

Data Index: 1564341 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 2.8121. Min Range: -2.8121

Max Act: 2.2278. Min Act: -0.0000

Data Index: 1561509 (Python Code)

Max Activating Token Index: 23