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

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

Neuron 602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.9417. Min Act: -0.0000

Data Index: 392596 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.7635. Min Act: -0.0000

Data Index: 1279656 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.4093. Min Act: -0.0000

Data Index: 115697 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.3592. Min Act: -0.0001

Data Index: 1205576 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.2773. Min Act: -0.0000

Data Index: 1287969 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.3059. Min Act: -0.0001

Data Index: 1039670 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.2270. Min Act: -0.0000

Data Index: 1103597 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.3109. Min Act: -0.0000

Data Index: 404493 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.1505. Min Act: -0.0000

Data Index: 216969 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.2671. Min Act: -0.0000

Data Index: 1191555 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.1466. Min Act: -0.0000

Data Index: 939521 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 2.9417. Min Range: -2.9417

Max Act: 1.9494. Min Act: -0.0000

Data Index: 815001 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.0325. Min Act: -0.0000

Data Index: 402829 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.3845. Min Act: -0.0000

Data Index: 515965 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.1443. Min Act: -0.0000

Data Index: 241337 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 2.9417. Min Range: -2.9417

Max Act: 1.8839. Min Act: -0.0000

Data Index: 375466 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.1113. Min Act: -0.0000

Data Index: 302165 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.0004. Min Act: -0.0000

Data Index: 603946 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 2.9417. Min Range: -2.9417

Max Act: 1.9748. Min Act: -0.0000

Data Index: 1150762 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.2147. Min Act: -0.0000

Data Index: 1062856 (C4 (Web Text))

Max Activating Token Index: 460