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

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

Neuron 2942 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: 0.3510. Min Range: -0.3510

Max Act: 0.3510. Min Act: -0.0001

Data Index: 103414 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2171. Min Act: -0.0001

Data Index: 522586 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2239. Min Act: -0.0001

Data Index: 208926 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2108. Min Act: -0.0000

Data Index: 515479 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2081. Min Act: -0.0000

Data Index: 816622 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1292054 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2019. Min Act: -0.0000

Data Index: 696973 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1949. Min Act: -0.0001

Data Index: 962577 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1351847 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1223310 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1759. Min Act: -0.0000

Data Index: 505041 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1868. Min Act: -0.0000

Data Index: 464079 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1839. Min Act: -0.0000

Data Index: 647071 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1089685 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1743. Min Act: -0.0000

Data Index: 186894 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1690. Min Act: -0.0000

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1672. Min Act: -0.0000

Data Index: 350546 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1770. Min Act: -0.0000

Data Index: 511915 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1762. Min Act: -0.0000

Data Index: 904237 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.1761. Min Act: -0.0000

Data Index: 109330 (C4 (Web Text))

Max Activating Token Index: 417