Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0000

Data Index: 101187 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1512. Min Act: -0.0000

Data Index: 514976 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1436. Min Act: -0.0000

Data Index: 756639 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1475. Min Act: -0.0000

Data Index: 212437 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1415. Min Act: -0.0000

Data Index: 30877 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1052180 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1325242 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1288. Min Act: -0.0000

Data Index: 149008 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1272840 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1185. Min Act: -0.0000

Data Index: 525052 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1243. Min Act: -0.0000

Data Index: 133813 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1212. Min Act: -0.0000

Data Index: 364170 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1246. Min Act: -0.0000

Data Index: 658332 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1016364 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1136. Min Act: -0.0000

Data Index: 94647 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1017927 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1300052 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1097. Min Act: -0.0000

Data Index: 980287 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1061. Min Act: -0.0000

Data Index: 320516 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1081033 (C4 (Web Text))

Max Activating Token Index: 220