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

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

Neuron 4722 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1857. Min Act: -0.0000

Data Index: 683007 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1584. Min Act: -0.0000

Data Index: 974317 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1498. Min Act: -0.0000

Data Index: 625495 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1363. Min Act: -0.0000

Data Index: 991004 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1284. Min Act: -0.0000

Data Index: 77339 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1333. Min Act: -0.0000

Data Index: 930484 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1287. Min Act: -0.0000

Data Index: 84191 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1218. Min Act: -0.0000

Data Index: 743025 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1237. Min Act: -0.0000

Data Index: 970163 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1175. Min Act: -0.0000

Data Index: 954628 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1199. Min Act: -0.0000

Data Index: 417055 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1140. Min Act: -0.0000

Data Index: 749592 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1166786 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1187. Min Act: -0.0000

Data Index: 989065 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1004372 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1113. Min Act: -0.0000

Data Index: 647660 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1169. Min Act: -0.0000

Data Index: 690030 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1155. Min Act: -0.0000

Data Index: 690037 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1093091 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1116. Min Act: -0.0000

Data Index: 611876 (C4 (Web Text))

Max Activating Token Index: 325