Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: -0.0003

Data Index: 560101 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0578. Min Act: -0.0003

Data Index: 311941 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1259069 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0577. Min Act: -0.0003

Data Index: 766344 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1224046 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0595. Min Act: -0.0003

Data Index: 470397 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0544. Min Act: -0.0003

Data Index: 739994 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0532. Min Act: -0.0003

Data Index: 16843 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0550. Min Act: -0.0003

Data Index: 736028 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1318366 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0535. Min Act: -0.0003

Data Index: 273795 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0579. Min Act: -0.0003

Data Index: 986280 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0551. Min Act: -0.0003

Data Index: 885241 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0472. Min Act: -0.0003

Data Index: 986993 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0561. Min Act: -0.0003

Data Index: 60104 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0535. Min Act: -0.0003

Data Index: 314514 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1130843 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1324323 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0527. Min Act: -0.0003

Data Index: 964387 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1178427 (C4 (Web Text))

Max Activating Token Index: 639