Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 52 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.2162. Min Act: -0.0000

Data Index: 163253 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.1397. Min Act: -0.0000

Data Index: 723644 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1267695 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.0080. Min Act: -0.0000

Data Index: 345522 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1153681 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8818. Min Act: -0.0000

Data Index: 256350 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8676. Min Act: -0.0000

Data Index: 265151 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1016663 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1117920 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8635. Min Act: -0.0000

Data Index: 397603 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1172934 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9181. Min Act: -0.0000

Data Index: 803926 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1084107 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9119. Min Act: -0.0000

Data Index: 982691 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8772. Min Act: -0.0000

Data Index: 863423 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8995. Min Act: -0.0000

Data Index: 739751 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8889. Min Act: -0.0000

Data Index: 188630 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8846. Min Act: -0.0000

Data Index: 291749 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8510. Min Act: -0.0000

Data Index: 5903 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8531. Min Act: -0.0000

Data Index: 745310 (C4 (Web Text))

Max Activating Token Index: 41