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

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

Neuron 3030 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4820. Min Range: -6.4820

Max Act: 6.4820. Min Act: -0.0000

Data Index: 327829 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 6.4820. Min Range: -6.4820

Max Act: 6.4209. Min Act: 0.0000

Data Index: 1050237 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 6.4820. Min Range: -6.4820

Max Act: 5.4736. Min Act: -0.0000

Data Index: 1502796 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.9742. Min Act: -0.0000

Data Index: 1487773 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 6.4820. Min Range: -6.4820

Max Act: 5.1174. Min Act: -0.0000

Data Index: 1408629 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.4558. Min Act: -0.0000

Data Index: 1539769 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.7566. Min Act: -0.0000

Data Index: 1458352 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 6.4820. Min Range: -6.4820

Max Act: 5.0201. Min Act: -0.0000

Data Index: 1632596 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.9828. Min Act: -0.0000

Data Index: 1637811 (Python Code)

Max Activating Token Index: 885

Text #9

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.6741. Min Act: -0.0000

Data Index: 1533846 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.4536. Min Act: -0.0000

Data Index: 1369532 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.2812. Min Act: -0.0000

Data Index: 1552991 (Python Code)

Max Activating Token Index: 523

Text #12

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.3907. Min Act: -0.0000

Data Index: 1645913 (Python Code)

Max Activating Token Index: 914

Text #13

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.1961. Min Act: -0.0000

Data Index: 1408225 (Python Code)

Max Activating Token Index: 346

Text #14

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.4705. Min Act: -0.0000

Data Index: 1518826 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.4745. Min Act: -0.0000

Data Index: 1564025 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.2856. Min Act: -0.0000

Data Index: 1477459 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.3226. Min Act: -0.0000

Data Index: 1655752 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.2118. Min Act: -0.0000

Data Index: 1360255 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 6.4820. Min Range: -6.4820

Max Act: 4.1755. Min Act: -0.0000

Data Index: 1460564 (Python Code)

Max Activating Token Index: 1012