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

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

Neuron 4391 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1255457 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1172775 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6605. Min Act: -0.0000

Data Index: 387901 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6201. Min Act: -0.0000

Data Index: 714860 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6301. Min Act: -0.0000

Data Index: 158694 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1080177 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6284. Min Act: -0.0000

Data Index: 565257 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1094754 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5970. Min Act: -0.0000

Data Index: 464936 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1278997 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1018260 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5927. Min Act: -0.0000

Data Index: 406506 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1202838 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5659. Min Act: -0.0000

Data Index: 891557 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5872. Min Act: -0.0000

Data Index: 619053 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6056. Min Act: -0.0000

Data Index: 951352 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1346485 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5615. Min Act: -0.0000

Data Index: 46431 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1227339 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5507. Min Act: -0.0000

Data Index: 686841 (C4 (Web Text))

Max Activating Token Index: 44