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

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

Neuron 1918 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: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0001

Data Index: 235790 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0653. Min Act: -0.0001

Data Index: 552202 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0642. Min Act: -0.0001

Data Index: 352343 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0677. Min Act: -0.0001

Data Index: 223017 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0631. Min Act: -0.0001

Data Index: 695154 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0613. Min Act: -0.0001

Data Index: 454264 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0586. Min Act: -0.0001

Data Index: 697878 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0623. Min Act: -0.0001

Data Index: 804681 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1607945 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1316376 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0594. Min Act: -0.0001

Data Index: 895977 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0556. Min Act: -0.0001

Data Index: 58924 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1122152 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0574. Min Act: -0.0001

Data Index: 814350 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1348338 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0607. Min Act: -0.0001

Data Index: 996681 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0576. Min Act: -0.0001

Data Index: 75804 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0558. Min Act: -0.0001

Data Index: 938518 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1197117 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0566. Min Act: -0.0001

Data Index: 738874 (C4 (Web Text))

Max Activating Token Index: 55