Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3866 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1288673 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5955. Min Act: -0.0001

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6108. Min Act: -0.0000

Data Index: 418560 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5688. Min Act: -0.0001

Data Index: 597531 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1045267 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5411. Min Act: -0.0000

Data Index: 66300 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5361. Min Act: -0.0000

Data Index: 855264 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5298. Min Act: -0.0000

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1213178 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1245427 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5071. Min Act: -0.0001

Data Index: 17373 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5248. Min Act: -0.0000

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5402. Min Act: -0.0000

Data Index: 258213 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5151. Min Act: -0.0001

Data Index: 778140 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4904. Min Act: -0.0000

Data Index: 516109 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1065034 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1145501 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1023228 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5213. Min Act: -0.0000

Data Index: 343342 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1269367 (C4 (Web Text))

Max Activating Token Index: 927