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

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

Neuron 65 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1170584 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4891. Min Act: -0.0000

Data Index: 460997 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4861. Min Act: -0.0000

Data Index: 376610 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4760. Min Act: -0.0000

Data Index: 768847 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4711. Min Act: -0.0000

Data Index: 527762 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4715. Min Act: -0.0000

Data Index: 716738 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4538. Min Act: -0.0000

Data Index: 26425 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4821. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4825. Min Act: -0.0000

Data Index: 992981 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4420. Min Act: -0.0000

Data Index: 432746 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4398. Min Act: -0.0000

Data Index: 830936 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4506. Min Act: -0.0000

Data Index: 283552 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4622. Min Act: -0.0000

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1336279 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1196373 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4328. Min Act: -0.0000

Data Index: 158356 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4279. Min Act: -0.0000

Data Index: 711497 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4212. Min Act: -0.0000

Data Index: 384335 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4091. Min Act: -0.0000

Data Index: 398351 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.5542. Min Range: -0.5542

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1019278 (C4 (Web Text))

Max Activating Token Index: 1007