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

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

Neuron 1238 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1985. Min Act: -0.0001

Data Index: 852479 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2100. Min Act: -0.0000

Data Index: 141201 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2099. Min Act: -0.0001

Data Index: 906941 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1024519 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2216. Min Act: -0.0000

Data Index: 4316 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2244. Min Act: -0.0000

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1976. Min Act: -0.0000

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1136954 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2082. Min Act: -0.0000

Data Index: 709259 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1000615 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1099601 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1928. Min Act: -0.0000

Data Index: 772167 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1033877 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2065. Min Act: -0.0001

Data Index: 440172 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2148. Min Act: -0.0000

Data Index: 490769 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1044865 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1302831 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1979. Min Act: -0.0000

Data Index: 155838 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2024. Min Act: -0.0000

Data Index: 129771 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1072023 (C4 (Web Text))

Max Activating Token Index: 644