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

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

Neuron 1100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.2090. Min Act: -0.0002

Data Index: 612282 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1753. Min Act: -0.0001

Data Index: 714705 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1204. Min Act: -0.0002

Data Index: 216029 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1278. Min Act: -0.0002

Data Index: 440769 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1281406 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1309. Min Act: -0.0001

Data Index: 447507 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1362. Min Act: -0.0001

Data Index: 146600 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1194. Min Act: -0.0002

Data Index: 649233 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1184. Min Act: -0.0002

Data Index: 151431 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1342311 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1188. Min Act: -0.0002

Data Index: 671686 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1203. Min Act: -0.0002

Data Index: 88022 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1126. Min Act: -0.0001

Data Index: 693096 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1202. Min Act: -0.0001

Data Index: 798557 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1147. Min Act: -0.0002

Data Index: 970118 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1196. Min Act: -0.0001

Data Index: 892847 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1179. Min Act: -0.0002

Data Index: 90217 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1202. Min Act: -0.0001

Data Index: 978247 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1352539 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.2090. Min Range: -0.2090

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1024180 (C4 (Web Text))

Max Activating Token Index: 322