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

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

Neuron 2002 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: 0.4770. Min Range: -0.4770

Max Act: 0.4770. Min Act: -0.0000

Data Index: 756231 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1099828 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1331595 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1250469 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3523. Min Act: -0.0000

Data Index: 474646 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3599. Min Act: -0.0000

Data Index: 97419 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1069953 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3488. Min Act: -0.0000

Data Index: 219325 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3373. Min Act: -0.0000

Data Index: 547523 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3368. Min Act: -0.0000

Data Index: 631819 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3216. Min Act: -0.0000

Data Index: 731823 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3218. Min Act: -0.0000

Data Index: 594372 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1310872 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3245. Min Act: -0.0000

Data Index: 470623 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1282413 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1321472 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3181. Min Act: -0.0000

Data Index: 864531 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.2876. Min Act: 0.0000

Data Index: 124220 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3335. Min Act: -0.0000

Data Index: 841970 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3225. Min Act: -0.0000

Data Index: 150276 (C4 (Web Text))

Max Activating Token Index: 63