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

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

Neuron 3153 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0525. Min Act: -0.0002

Data Index: 742883 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0002

Data Index: 913031 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0400. Min Act: -0.0002

Data Index: 155177 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0406. Min Act: -0.0002

Data Index: 551873 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0384. Min Act: -0.0002

Data Index: 438474 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0346. Min Act: -0.0002

Data Index: 162568 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0374. Min Act: -0.0002

Data Index: 199440 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0384. Min Act: -0.0002

Data Index: 237344 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1163764 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0392. Min Act: -0.0002

Data Index: 388907 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0423. Min Act: -0.0002

Data Index: 735082 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0380. Min Act: -0.0002

Data Index: 493741 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0380. Min Act: -0.0002

Data Index: 649997 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0345. Min Act: -0.0002

Data Index: 324476 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0367. Min Act: -0.0002

Data Index: 846876 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0355. Min Act: -0.0002

Data Index: 858115 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1077344 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0368. Min Act: -0.0002

Data Index: 237185 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0418. Min Act: -0.0002

Data Index: 435393 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0358. Min Act: -0.0002

Data Index: 422646 (C4 (Web Text))

Max Activating Token Index: 483