Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0001

Data Index: 294567 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0728. Min Act: -0.0000

Data Index: 809139 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1148283 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0704. Min Act: -0.0001

Data Index: 861167 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1258236 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0677. Min Act: -0.0000

Data Index: 180578 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0676. Min Act: -0.0000

Data Index: 318208 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1095167 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0642. Min Act: -0.0000

Data Index: 743243 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0644. Min Act: -0.0001

Data Index: 517369 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1256332 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0636. Min Act: -0.0000

Data Index: 114377 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1048946 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0629. Min Act: -0.0001

Data Index: 949122 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0612. Min Act: -0.0000

Data Index: 579883 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1206534 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0638. Min Act: -0.0001

Data Index: 615444 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0612. Min Act: -0.0001

Data Index: 9978 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0633. Min Act: -0.0001

Data Index: 269733 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0611. Min Act: -0.0001

Data Index: 964891 (C4 (Web Text))

Max Activating Token Index: 839