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

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

Neuron 4216 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.8498. Min Act: -0.0000

Data Index: 275390 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.8168. Min Act: -0.0000

Data Index: 296536 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7879. Min Act: -0.0000

Data Index: 61737 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.8243. Min Act: -0.0000

Data Index: 560090 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7569. Min Act: -0.0000

Data Index: 389607 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1058181 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7254. Min Act: -0.0000

Data Index: 126009 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6883. Min Act: -0.0000

Data Index: 853847 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1045561 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1029726 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6382. Min Act: -0.0000

Data Index: 933563 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6114. Min Act: -0.0000

Data Index: 719485 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1141184 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1146092 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6293. Min Act: -0.0000

Data Index: 694614 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6227. Min Act: -0.0000

Data Index: 559621 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.5997. Min Act: -0.0000

Data Index: 771239 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6328. Min Act: -0.0000

Data Index: 136054 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1144476 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.8498. Min Range: -0.8498

Max Act: 0.5929. Min Act: -0.0000

Data Index: 643876 (C4 (Web Text))

Max Activating Token Index: 677