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

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

Neuron 3002 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1423. Min Act: -0.0000

Data Index: 880500 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1129. Min Act: -0.0000

Data Index: 449324 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1191. Min Act: -0.0000

Data Index: 615363 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1147. Min Act: -0.0000

Data Index: 774851 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1136. Min Act: -0.0000

Data Index: 87279 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1013. Min Act: -0.0000

Data Index: 467692 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1040. Min Act: -0.0000

Data Index: 601229 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1033563 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.1014. Min Act: -0.0000

Data Index: 971739 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1219135 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0915. Min Act: -0.0000

Data Index: 689887 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0907. Min Act: -0.0000

Data Index: 895586 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1124455 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1214766 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0943. Min Act: -0.0000

Data Index: 440789 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0927. Min Act: -0.0000

Data Index: 913884 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1073082 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1140370 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1255576 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1423. Min Range: -0.1423

Max Act: 0.0794. Min Act: -0.0000

Data Index: 77237 (C4 (Web Text))

Max Activating Token Index: 990