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

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

Neuron 5807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.6033. Min Act: -0.0001

Data Index: 330649 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3838. Min Act: -0.0001

Data Index: 1573780 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3317. Min Act: -0.0001

Data Index: 1211548 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2007. Min Act: -0.0001

Data Index: 65636 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.6161. Min Act: -0.0001

Data Index: 1589118 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3078. Min Act: -0.0001

Data Index: 684196 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3778. Min Act: -0.0001

Data Index: 558527 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2971. Min Act: -0.0001

Data Index: 448667 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1650. Min Act: -0.0001

Data Index: 226792 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3000. Min Act: -0.0001

Data Index: 643066 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1436. Min Act: -0.0001

Data Index: 556363 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3135. Min Act: -0.0001

Data Index: 247698 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.0739. Min Act: -0.0001

Data Index: 164880 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2308. Min Act: -0.0001

Data Index: 1105337 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2265. Min Act: -0.0001

Data Index: 534077 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2246. Min Act: -0.0001

Data Index: 1029026 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.1840. Min Act: -0.0001

Data Index: 1085205 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.0364. Min Act: -0.0001

Data Index: 1203988 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.3297. Min Act: -0.0001

Data Index: 985191 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 1.6161. Min Range: -1.6161

Max Act: 1.2403. Min Act: -0.0001

Data Index: 1396789 (Python Code)

Max Activating Token Index: 539