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

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

Neuron 3462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0765. Min Act: -0.0001

Data Index: 226932 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0672. Min Act: -0.0001

Data Index: 609717 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0001

Data Index: 353067 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1336712 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1324410 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0649. Min Act: -0.0001

Data Index: 675797 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0650. Min Act: -0.0001

Data Index: 603236 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0588. Min Act: -0.0001

Data Index: 64969 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0627. Min Act: -0.0001

Data Index: 629288 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0647. Min Act: -0.0001

Data Index: 214856 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1016325 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0628. Min Act: -0.0001

Data Index: 868143 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0678. Min Act: -0.0001

Data Index: 832031 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0638. Min Act: -0.0001

Data Index: 983584 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0583. Min Act: -0.0001

Data Index: 760304 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0603. Min Act: -0.0001

Data Index: 288073 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1204638 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0581. Min Act: -0.0001

Data Index: 27853 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0594. Min Act: -0.0001

Data Index: 527933 (C4 (Web Text))

Max Activating Token Index: 195