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

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

Neuron 1505 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.9194. Min Act: -0.0001

Data Index: 187748 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8962. Min Act: -0.0001

Data Index: 741321 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8596. Min Act: -0.0001

Data Index: 578035 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8309. Min Act: -0.0001

Data Index: 873442 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1244422 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8024. Min Act: -0.0001

Data Index: 637225 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7575. Min Act: -0.0001

Data Index: 1307149 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7497. Min Act: -0.0001

Data Index: 902050 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7700. Min Act: -0.0001

Data Index: 734677 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7376. Min Act: -0.0001

Data Index: 479764 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7599. Min Act: -0.0001

Data Index: 264734 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1069139 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7820. Min Act: -0.0001

Data Index: 49003 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.6975. Min Act: -0.0001

Data Index: 83366 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7235. Min Act: -0.0001

Data Index: 40053 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7460. Min Act: -0.0001

Data Index: 114216 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7088. Min Act: -0.0001

Data Index: 261493 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7137. Min Act: -0.0001

Data Index: 223170 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7368. Min Act: -0.0001

Data Index: 550736 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.7201. Min Act: -0.0001

Data Index: 902880 (C4 (Web Text))

Max Activating Token Index: 225