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

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

Neuron 5853 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.8095. Min Act: -0.0000

Data Index: 733996 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.7710. Min Act: -0.0000

Data Index: 587281 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6305. Min Act: -0.0000

Data Index: 757016 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1267065 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6618. Min Act: -0.0000

Data Index: 185860 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6238. Min Act: -0.0000

Data Index: 171466 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6165. Min Act: -0.0000

Data Index: 958997 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.6648. Min Act: -0.0000

Data Index: 151700 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5832. Min Act: -0.0000

Data Index: 928572 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5707. Min Act: -0.0000

Data Index: 132965 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5855. Min Act: -0.0000

Data Index: 435126 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5794. Min Act: -0.0000

Data Index: 422302 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5954. Min Act: -0.0000

Data Index: 181292 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5697. Min Act: -0.0000

Data Index: 453301 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5464. Min Act: -0.0000

Data Index: 68111 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5789. Min Act: -0.0000

Data Index: 627272 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5453. Min Act: -0.0000

Data Index: 126426 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1065221 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1378498 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.8095. Min Range: -0.8095

Max Act: 0.5568. Min Act: -0.0000

Data Index: 707536 (C4 (Web Text))

Max Activating Token Index: 681