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

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

Neuron 2663 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.9168. Min Act: -0.0000

Data Index: 622098 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.8661. Min Act: 0.0000

Data Index: 498303 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.8575. Min Act: -0.0000

Data Index: 778643 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.9017. Min Act: -0.0000

Data Index: 792357 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1117725 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1521361 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.8003. Min Act: -0.0000

Data Index: 586085 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.8446. Min Act: -0.0000

Data Index: 322144 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7796. Min Act: -0.0000

Data Index: 371451 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7291. Min Act: 0.0000

Data Index: 1493596 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1551622 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7373. Min Act: 0.0000

Data Index: 698796 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1502351 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1426382 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1307416 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1106011 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7375. Min Act: -0.0000

Data Index: 538580 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7383. Min Act: 0.0001

Data Index: 867810 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1601427 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.9168. Min Range: -0.9168

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1477533 (Python Code)

Max Activating Token Index: 523