Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 191 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0001

Data Index: 987868 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1460. Min Act: -0.0001

Data Index: 74748 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1503. Min Act: -0.0001

Data Index: 833871 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1504. Min Act: -0.0001

Data Index: 199596 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1414. Min Act: -0.0001

Data Index: 729517 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1408. Min Act: -0.0001

Data Index: 417828 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1423. Min Act: -0.0001

Data Index: 15789 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1309. Min Act: -0.0001

Data Index: 423045 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1228. Min Act: -0.0001

Data Index: 345081 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1269. Min Act: -0.0001

Data Index: 101414 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1222. Min Act: -0.0001

Data Index: 62899 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1207. Min Act: -0.0001

Data Index: 763374 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1245. Min Act: -0.0001

Data Index: 957227 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1119609 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1189. Min Act: -0.0001

Data Index: 477693 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1217930 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1182. Min Act: -0.0001

Data Index: 629341 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1168. Min Act: -0.0001

Data Index: 73651 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1151349 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1294. Min Act: -0.0001

Data Index: 508796 (C4 (Web Text))

Max Activating Token Index: 803