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

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

Neuron 4175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3702. Min Act: -0.0000

Data Index: 173122 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1065870 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3777. Min Act: -0.0000

Data Index: 188875 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3651. Min Act: -0.0000

Data Index: 468884 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1043728 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3451. Min Act: -0.0000

Data Index: 382116 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3240. Min Act: -0.0000

Data Index: 72392 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3473. Min Act: -0.0000

Data Index: 93186 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1243214 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3600. Min Act: -0.0000

Data Index: 10968 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3301. Min Act: -0.0000

Data Index: 26911 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2885. Min Act: -0.0000

Data Index: 940760 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1069019 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1343992 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3131. Min Act: -0.0000

Data Index: 790054 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2697. Min Act: -0.0000

Data Index: 718337 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2705. Min Act: -0.0000

Data Index: 912499 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2615. Min Act: -0.0000

Data Index: 475067 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2617. Min Act: -0.0000

Data Index: 641444 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2667. Min Act: -0.0000

Data Index: 962622 (C4 (Web Text))

Max Activating Token Index: 481