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

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

Neuron 4030 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: 5.8513. Min Range: -5.8513

Max Act: 5.7958. Min Act: -0.0000

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.8263. Min Act: -0.0000

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.8513. Min Act: -0.0000

Data Index: 845859 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.6178. Min Act: -0.0000

Data Index: 76753 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.6289. Min Act: -0.0000

Data Index: 217546 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.5191. Min Act: -0.0000

Data Index: 942833 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.6957. Min Act: -0.0000

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.4345. Min Act: -0.0000

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.3425. Min Act: -0.0000

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.2653. Min Act: -0.0000

Data Index: 1091753 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.2734. Min Act: -0.0000

Data Index: 487738 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.2544. Min Act: -0.0000

Data Index: 647508 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.3922. Min Act: -0.0000

Data Index: 510205 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 5.8513. Min Range: -5.8513

Max Act: 5.3363. Min Act: -0.0000

Data Index: 913062 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 5.8513. Min Range: -5.8513

Max Act: 4.5077. Min Act: -0.0000

Data Index: 460433 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 5.8513. Min Range: -5.8513

Max Act: 4.4709. Min Act: -0.0000

Data Index: 499316 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 5.8513. Min Range: -5.8513

Max Act: 4.6525. Min Act: -0.0000

Data Index: 1090366 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.8513. Min Range: -5.8513

Max Act: 4.3821. Min Act: -0.0000

Data Index: 703722 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 5.8513. Min Range: -5.8513

Max Act: 4.5586. Min Act: -0.0000

Data Index: 101097 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 5.8513. Min Range: -5.8513

Max Act: 4.2383. Min Act: -0.0000

Data Index: 175453 (C4 (Web Text))

Max Activating Token Index: 290