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

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

Neuron 1877 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: 1.3812. Min Range: -1.3812

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1325704 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1338845 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1604824 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.1531. Min Act: -0.0000

Data Index: 48570 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1656901 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1586737 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1429731 (Python Code)

Max Activating Token Index: 967

Text #7

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0566. Min Act: -0.0000

Data Index: 750934 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1296488 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1572997 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1415042 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1614731 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1065185 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1386158 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1396930 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1103282 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.3812. Min Range: -1.3812

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1320547 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1587920 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 1.3812. Min Range: -1.3812

Max Act: 0.9044. Min Act: -0.0000

Data Index: 172048 (C4 (Web Text))

Max Activating Token Index: 56