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

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

Neuron 4650 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1560086 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0001

Data Index: 512714 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1630188 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0825. Min Act: -0.0001

Data Index: 113404 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1420221 (Python Code)

Max Activating Token Index: 189

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1396560 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1484966 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1371037 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1308843 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1362849 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1336875 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1519241 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1525291 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1480746 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1459624 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1607477 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1193363 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1319755 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0746. Min Act: -0.0001

Data Index: 167752 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0752. Min Act: -0.0001

Data Index: 169828 (C4 (Web Text))

Max Activating Token Index: 242