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

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

Neuron 1849 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6341. Min Range: -3.6341

Max Act: 3.6341. Min Act: -0.0000

Data Index: 912499 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.6341. Min Range: -3.6341

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1343992 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 3.6341. Min Range: -3.6341

Max Act: 2.3982. Min Act: -0.0000

Data Index: 529242 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 3.6341. Min Range: -3.6341

Max Act: 2.3174. Min Act: -0.0000

Data Index: 249578 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1231215 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1183321 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1325497 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1034937 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1106325 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.2615. Min Act: -0.0000

Data Index: 801576 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1051275 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1162758 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.1728. Min Act: -0.0000

Data Index: 169219 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1103975 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.1317. Min Act: -0.0000

Data Index: 820843 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.1293. Min Act: -0.0000

Data Index: 394669 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.1257. Min Act: -0.0000

Data Index: 218684 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.1022. Min Act: -0.0000

Data Index: 478506 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 3.6341. Min Range: -3.6341

Max Act: 1.0526. Min Act: -0.0000

Data Index: 237837 (C4 (Web Text))

Max Activating Token Index: 585