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

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

Neuron 4877 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8830. Min Range: -2.8830

Max Act: 2.8830. Min Act: -0.0000

Data Index: 87440 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 2.8830. Min Range: -2.8830

Max Act: 2.5173. Min Act: -0.0000

Data Index: 1094770 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 2.8830. Min Range: -2.8830

Max Act: 2.4800. Min Act: -0.0000

Data Index: 451433 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1180345 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1480261 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1365340 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1602948 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.5363. Min Act: -0.0000

Data Index: 1600332 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1493567 (Python Code)

Max Activating Token Index: 533

Text #9

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1565679 (Python Code)

Max Activating Token Index: 156

Text #10

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1463446 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1428689 (Python Code)

Max Activating Token Index: 182

Text #12

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.3046. Min Act: -0.0000

Data Index: 1536703 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1389306 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1481869 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1648465 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1627389 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1537790 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 2.8830. Min Range: -2.8830

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1575234 (Python Code)

Max Activating Token Index: 947