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

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

Neuron 4588 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1158907 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3227. Min Act: -0.0000

Data Index: 768549 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3313. Min Act: -0.0000

Data Index: 812705 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3067. Min Act: -0.0000

Data Index: 611044 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3054. Min Act: -0.0000

Data Index: 787944 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1333064 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3129. Min Act: -0.0000

Data Index: 578023 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1587254 (Python Code)

Max Activating Token Index: 910

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1262286 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1111856 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2813. Min Act: -0.0000

Data Index: 777715 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2889. Min Act: -0.0000

Data Index: 749060 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2785. Min Act: -0.0000

Data Index: 638243 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2848. Min Act: -0.0000

Data Index: 997980 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2643. Min Act: -0.0000

Data Index: 813633 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1337995 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1120950 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2630. Min Act: -0.0000

Data Index: 682973 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2622. Min Act: -0.0000

Data Index: 146984 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2671. Min Act: -0.0000

Data Index: 888321 (C4 (Web Text))

Max Activating Token Index: 862