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

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

Neuron 988 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0371. Min Range: -3.0371

Max Act: 3.0371. Min Act: -0.0000

Data Index: 918349 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0980. Min Act: -0.0000

Data Index: 846694 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0264. Min Act: -0.0000

Data Index: 260932 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0901. Min Act: -0.0000

Data Index: 146432 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0850. Min Act: -0.0000

Data Index: 41877 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0367. Min Act: -0.0000

Data Index: 1173436 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0807. Min Act: -0.0000

Data Index: 1198743 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.0913. Min Act: -0.0000

Data Index: 852087 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.9675. Min Act: -0.0000

Data Index: 887744 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.8230. Min Act: -0.0000

Data Index: 42623 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.9104. Min Act: -0.0000

Data Index: 389731 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1264557 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.8699. Min Act: -0.0000

Data Index: 155232 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.8703. Min Act: -0.0000

Data Index: 144461 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.8491. Min Act: -0.0000

Data Index: 700186 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 3.0371. Min Range: -3.0371

Max Act: 2.1066. Min Act: -0.0000

Data Index: 312095 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.8013. Min Act: -0.0000

Data Index: 408551 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.7933. Min Act: -0.0000

Data Index: 591196 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1097103 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 3.0371. Min Range: -3.0371

Max Act: 1.7709. Min Act: -0.0000

Data Index: 173460 (C4 (Web Text))

Max Activating Token Index: 489