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

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

Neuron 3702 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: 0.2727. Min Range: -0.2727

Max Act: 0.2727. Min Act: -0.0000

Data Index: 376962 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2512. Min Act: 0.0001

Data Index: 120835 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2340. Min Act: -0.0000

Data Index: 768636 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2395. Min Act: -0.0000

Data Index: 204696 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2136. Min Act: -0.0000

Data Index: 552207 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2121. Min Act: -0.0001

Data Index: 243027 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1191848 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2011. Min Act: -0.0000

Data Index: 957177 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2067. Min Act: -0.0000

Data Index: 968572 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2073. Min Act: -0.0000

Data Index: 827819 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2027. Min Act: -0.0000

Data Index: 180727 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1992. Min Act: -0.0000

Data Index: 105252 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1912. Min Act: -0.0000

Data Index: 41898 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1975. Min Act: -0.0000

Data Index: 459936 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1955. Min Act: -0.0000

Data Index: 801628 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1000751 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.2025. Min Act: -0.0000

Data Index: 294549 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1090372 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1349988 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.2727. Min Range: -0.2727

Max Act: 0.1931. Min Act: -0.0000

Data Index: 910433 (C4 (Web Text))

Max Activating Token Index: 911