Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2206 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2404. Min Act: -0.0000

Data Index: 30397 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2066. Min Act: -0.0001

Data Index: 557560 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1972. Min Act: -0.0001

Data Index: 257745 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1322447 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1979. Min Act: -0.0001

Data Index: 55682 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1851. Min Act: -0.0001

Data Index: 856892 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1068743 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1353857 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1865. Min Act: -0.0001

Data Index: 499232 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1760. Min Act: -0.0001

Data Index: 408093 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1780. Min Act: -0.0001

Data Index: 507586 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1887. Min Act: -0.0001

Data Index: 52523 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1886. Min Act: -0.0000

Data Index: 925466 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1051929 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1690. Min Act: -0.0001

Data Index: 549404 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1741. Min Act: -0.0001

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1740. Min Act: -0.0001

Data Index: 191799 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1062998 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1151037 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1676. Min Act: -0.0001

Data Index: 217478 (C4 (Web Text))

Max Activating Token Index: 438