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

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

Neuron 2706 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.4594. Min Act: 0.0000

Data Index: 1222104 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1316992 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.4594. Min Range: -1.4594

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1111049 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.9339. Min Act: -0.0000

Data Index: 245523 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.9150. Min Act: -0.0000

Data Index: 322638 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1246034 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1243591 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.8523. Min Act: -0.0000

Data Index: 721742 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1119145 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.8405. Min Act: -0.0000

Data Index: 734580 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1232166 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1322698 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1211819 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.8090. Min Act: -0.0000

Data Index: 185473 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7394. Min Act: -0.0000

Data Index: 230636 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7695. Min Act: -0.0000

Data Index: 922308 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1309155 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7158. Min Act: -0.0000

Data Index: 861341 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7313. Min Act: -0.0000

Data Index: 824983 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.4594. Min Range: -1.4594

Max Act: 0.7518. Min Act: 0.0000

Data Index: 1011597 (C4 (Web Text))

Max Activating Token Index: 414