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

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

Neuron 3867 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.7407. Min Act: -0.0000

Data Index: 360825 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.7253. Min Act: 0.0002

Data Index: 447411 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.5247. Min Act: 0.0000

Data Index: 785399 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.5070. Min Act: -0.0000

Data Index: 171172 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.5177. Min Act: 0.0001

Data Index: 1227208 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3776. Min Act: -0.0000

Data Index: 782257 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.4276. Min Act: -0.0000

Data Index: 650997 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3204. Min Act: 0.0001

Data Index: 673548 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.4838. Min Act: -0.0000

Data Index: 62307 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3733. Min Act: -0.0000

Data Index: 16962 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.3174. Min Act: 0.0001

Data Index: 369367 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2614. Min Act: -0.0000

Data Index: 568960 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1198317 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0965. Min Act: -0.0000

Data Index: 213345 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0686. Min Act: -0.0000

Data Index: 21780 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0912. Min Act: -0.0000

Data Index: 799282 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.2864. Min Act: -0.0000

Data Index: 223063 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9953. Min Act: 0.0000

Data Index: 808469 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.7407. Min Range: -1.7407

Max Act: 0.9880. Min Act: 0.0001

Data Index: 1285485 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.7407. Min Range: -1.7407

Max Act: 1.0285. Min Act: -0.0000

Data Index: 278372 (C4 (Web Text))

Max Activating Token Index: 795