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

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

Neuron 2826 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.2551. Min Act: -0.0001

Data Index: 526744 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.1985. Min Act: -0.0001

Data Index: 246418 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.1207. Min Act: -0.0001

Data Index: 664616 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.0807. Min Act: -0.0001

Data Index: 818331 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.0878. Min Act: -0.0001

Data Index: 979589 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.1065. Min Act: -0.0001

Data Index: 738323 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.1371. Min Act: -0.0001

Data Index: 544649 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.0153. Min Act: -0.0001

Data Index: 1100474 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1430496 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9300. Min Act: -0.0001

Data Index: 1555437 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9867. Min Act: -0.0001

Data Index: 1160663 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1436923 (Python Code)

Max Activating Token Index: 564

Text #12

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9767. Min Act: -0.0001

Data Index: 950123 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.0015. Min Act: -0.0001

Data Index: 690241 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.2551. Min Range: -1.2551

Max Act: 1.0065. Min Act: -0.0001

Data Index: 1389855 (Python Code)

Max Activating Token Index: 368

Text #15

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9816. Min Act: -0.0001

Data Index: 410681 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9403. Min Act: -0.0001

Data Index: 436730 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1646961 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1194010 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.2551. Min Range: -1.2551

Max Act: 0.9276. Min Act: -0.0001

Data Index: 291761 (C4 (Web Text))

Max Activating Token Index: 601