Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 855 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1549. Min Act: -0.0001

Data Index: 524795 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1481. Min Act: -0.0001

Data Index: 525711 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1278231 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1387. Min Act: -0.0001

Data Index: 86458 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1187. Min Act: -0.0001

Data Index: 300253 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1129. Min Act: -0.0001

Data Index: 652827 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1107. Min Act: -0.0001

Data Index: 305676 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1210. Min Act: -0.0001

Data Index: 245139 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1151829 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1055103 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1236. Min Act: -0.0001

Data Index: 810911 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1010. Min Act: -0.0001

Data Index: 339496 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1131. Min Act: -0.0001

Data Index: 125726 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1182. Min Act: -0.0001

Data Index: 748626 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1072. Min Act: -0.0001

Data Index: 625293 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1024426 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1105377 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.0990. Min Act: -0.0001

Data Index: 549256 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1086. Min Act: -0.0001

Data Index: 568260 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1059628 (C4 (Web Text))

Max Activating Token Index: 598