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

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

Neuron 3861 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: 0.1661. Min Range: -0.1661

Max Act: 0.1661. Min Act: -0.0001

Data Index: 961707 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1358124 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1320. Min Act: -0.0001

Data Index: 806816 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1291091 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1310. Min Act: -0.0000

Data Index: 839919 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1207. Min Act: -0.0000

Data Index: 903016 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1206. Min Act: -0.0001

Data Index: 255715 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1124. Min Act: -0.0001

Data Index: 505145 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1036399 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1182. Min Act: -0.0001

Data Index: 61691 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1179. Min Act: -0.0001

Data Index: 494799 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1159962 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1295809 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1221. Min Act: -0.0001

Data Index: 480004 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1113. Min Act: -0.0001

Data Index: 651218 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1197. Min Act: -0.0001

Data Index: 443454 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1185. Min Act: -0.0001

Data Index: 4482 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1068680 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1217. Min Act: -0.0001

Data Index: 604177 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1092. Min Act: -0.0001

Data Index: 783456 (C4 (Web Text))

Max Activating Token Index: 525