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

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

Neuron 1148 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3452. Min Act: -0.0000

Data Index: 261327 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3521. Min Act: -0.0000

Data Index: 744841 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3261. Min Act: -0.0000

Data Index: 303288 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3035. Min Act: -0.0000

Data Index: 509796 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2959. Min Act: -0.0000

Data Index: 463978 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1257117 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2924. Min Act: -0.0000

Data Index: 340587 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2860. Min Act: -0.0000

Data Index: 623849 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2719. Min Act: -0.0000

Data Index: 246072 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2588. Min Act: -0.0000

Data Index: 245886 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2650. Min Act: -0.0000

Data Index: 697662 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2702. Min Act: -0.0000

Data Index: 880788 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2700. Min Act: -0.0000

Data Index: 270278 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1274854 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2631. Min Act: -0.0000

Data Index: 479634 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2659. Min Act: -0.0000

Data Index: 911290 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1262892 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2597. Min Act: -0.0000

Data Index: 989910 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1124746 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2733. Min Act: -0.0000

Data Index: 754926 (C4 (Web Text))

Max Activating Token Index: 549