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

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

Neuron 2217 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: 0.6884. Min Range: -0.6884

Max Act: 0.6884. Min Act: -0.0000

Data Index: 274543 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6328. Min Act: -0.0000

Data Index: 67350 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6336. Min Act: -0.0000

Data Index: 91163 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.6219. Min Act: -0.0000

Data Index: 44216 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5895. Min Act: -0.0000

Data Index: 588518 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5638. Min Act: -0.0000

Data Index: 622901 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5491. Min Act: -0.0000

Data Index: 694935 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5683. Min Act: 0.0000

Data Index: 858384 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5486. Min Act: 0.0000

Data Index: 805721 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1257251 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5709. Min Act: 0.0000

Data Index: 1245602 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5316. Min Act: 0.0000

Data Index: 1301105 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5475. Min Act: 0.0000

Data Index: 1017974 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5247. Min Act: 0.0000

Data Index: 268516 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5182. Min Act: -0.0000

Data Index: 587308 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5294. Min Act: 0.0000

Data Index: 819704 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1205823 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.4915. Min Act: 0.0000

Data Index: 1153972 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.5209. Min Act: 0.0000

Data Index: 163235 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.6884. Min Range: -0.6884

Max Act: 0.4651. Min Act: 0.0000

Data Index: 660806 (C4 (Web Text))

Max Activating Token Index: 231