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

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

Neuron 2174 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.8467. Min Act: -0.0000

Data Index: 536517 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.6753. Min Act: -0.0000

Data Index: 267944 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.5230. Min Act: -0.0000

Data Index: 668473 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.1547. Min Act: -0.0000

Data Index: 1252251 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9367. Min Act: -0.0000

Data Index: 643641 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.0281. Min Act: -0.0000

Data Index: 675921 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1571488 (Python Code)

Max Activating Token Index: 398

Text #7

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9209. Min Act: -0.0000

Data Index: 163255 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.8510. Min Act: -0.0000

Data Index: 41509 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.6421. Min Act: -0.0000

Data Index: 742637 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.8181. Min Act: -0.0000

Data Index: 605012 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1331723 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.5402. Min Act: -0.0000

Data Index: 245209 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1614642 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1466956 (Python Code)

Max Activating Token Index: 235

Text #15

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1153609 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1636928 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1609915 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.3956. Min Act: 0.0000

Data Index: 687775 (C4 (Web Text))

Max Activating Token Index: 1020