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

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

Neuron 4170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3781. Min Act: -0.0000

Data Index: 24919 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1183096 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3121. Min Act: -0.0000

Data Index: 180228 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1225079 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3043. Min Act: -0.0000

Data Index: 936838 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.3077. Min Act: -0.0000

Data Index: 475155 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2722. Min Act: -0.0000

Data Index: 283036 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2788. Min Act: -0.0000

Data Index: 670734 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1375818 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1178184 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2520. Min Act: -0.0000

Data Index: 101752 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1541654 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2646. Min Act: -0.0000

Data Index: 609172 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1233898 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2529. Min Act: -0.0000

Data Index: 133273 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2533. Min Act: -0.0000

Data Index: 644666 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2653. Min Act: -0.0000

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1544981 (Python Code)

Max Activating Token Index: 987

Text #18

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2576. Min Act: -0.0000

Data Index: 801673 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.3781. Min Range: -0.3781

Max Act: 0.2819. Min Act: -0.0000

Data Index: 580290 (C4 (Web Text))

Max Activating Token Index: 732