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

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

Neuron 2944 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.9091. Min Act: -0.0000

Data Index: 123137 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.7636. Min Act: -0.0000

Data Index: 1504546 (Python Code)

Max Activating Token Index: 733

Text #2

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.4532. Min Act: -0.0000

Data Index: 721897 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.4215. Min Act: -0.0000

Data Index: 1591386 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.3940. Min Act: -0.0000

Data Index: 1589696 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.3736. Min Act: -0.0000

Data Index: 1434773 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.3990. Min Act: -0.0000

Data Index: 1177824 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.4715. Min Act: -0.0000

Data Index: 1402816 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1504295 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1486420 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.2830. Min Act: -0.0000

Data Index: 1652849 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.2923. Min Act: -0.0000

Data Index: 1503769 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.1486. Min Act: -0.0000

Data Index: 1550924 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.4000. Min Act: -0.0000

Data Index: 1478372 (Python Code)

Max Activating Token Index: 182

Text #14

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.2576. Min Act: -0.0000

Data Index: 828577 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.2384. Min Act: -0.0000

Data Index: 19458 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.3338. Min Act: -0.0000

Data Index: 1370000 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.0976. Min Act: -0.0000

Data Index: 1592045 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.1007. Min Act: -0.0000

Data Index: 1432157 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 2.9091. Min Range: -2.9091

Max Act: 2.0985. Min Act: -0.0000

Data Index: 1649790 (Python Code)

Max Activating Token Index: 1001