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

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

Neuron 2903 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1011169 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2848. Min Act: -0.0000

Data Index: 602914 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2633. Min Act: -0.0000

Data Index: 633847 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1097024 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1148478 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2756. Min Act: -0.0000

Data Index: 715370 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1538459 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3121. Min Act: -0.0000

Data Index: 475909 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2909. Min Act: -0.0000

Data Index: 528669 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2715. Min Act: -0.0000

Data Index: 510372 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2475. Min Act: -0.0000

Data Index: 135073 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2658. Min Act: -0.0000

Data Index: 187997 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2669. Min Act: -0.0000

Data Index: 77895 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2396. Min Act: -0.0000

Data Index: 629220 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2438. Min Act: -0.0000

Data Index: 352351 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2392. Min Act: -0.0000

Data Index: 927227 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1645574 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1226703 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1174369 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2391. Min Act: -0.0000

Data Index: 599456 (C4 (Web Text))

Max Activating Token Index: 781