Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 675 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.6562. Min Act: -0.0000

Data Index: 1283463 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.7953. Min Act: -0.0000

Data Index: 108099 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.6309. Min Act: -0.0000

Data Index: 1312539 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.5886. Min Act: -0.0000

Data Index: 450747 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4169. Min Act: -0.0000

Data Index: 481433 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.4923. Min Act: -0.0000

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.2896. Min Act: -0.0000

Data Index: 253332 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.1175. Min Act: -0.0000

Data Index: 590379 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.1790. Min Act: -0.0000

Data Index: 717591 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.1222. Min Act: -0.0000

Data Index: 925628 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.8641. Min Act: -0.0000

Data Index: 318757 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.0122. Min Act: -0.0000

Data Index: 314878 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9973. Min Act: -0.0000

Data Index: 1288423 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9744. Min Act: -0.0000

Data Index: 1036194 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 4.7953. Min Range: -4.7953

Max Act: 4.1201. Min Act: -0.0000

Data Index: 333478 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9085. Min Act: -0.0000

Data Index: 61042 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9532. Min Act: -0.0000

Data Index: 288757 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.9080. Min Act: -0.0000

Data Index: 411560 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.5971. Min Act: -0.0000

Data Index: 628607 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 4.7953. Min Range: -4.7953

Max Act: 3.8560. Min Act: -0.0000

Data Index: 643815 (C4 (Web Text))

Max Activating Token Index: 732