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

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

Neuron 3905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.5013. Min Act: -0.0000

Data Index: 885612 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.7005. Min Act: -0.0001

Data Index: 1244852 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.2408. Min Act: -0.0001

Data Index: 1228479 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.2055. Min Act: -0.0000

Data Index: 441458 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.4945. Min Act: -0.0001

Data Index: 328334 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.4534. Min Act: -0.0000

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.2460. Min Act: -0.0000

Data Index: 998004 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.2392. Min Act: -0.0000

Data Index: 441076 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.2135. Min Act: -0.0000

Data Index: 253111 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.0811. Min Act: -0.0000

Data Index: 359548 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.2634. Min Act: -0.0001

Data Index: 1204953 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.1111. Min Act: -0.0001

Data Index: 1238274 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.0764. Min Act: -0.0000

Data Index: 1177142 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 3.7005. Min Range: -3.7005

Max Act: 2.9351. Min Act: -0.0001

Data Index: 609073 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.0858. Min Act: -0.0001

Data Index: 1179752 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 3.7005. Min Range: -3.7005

Max Act: 2.9887. Min Act: -0.0001

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.7005. Min Range: -3.7005

Max Act: 2.8223. Min Act: -0.0001

Data Index: 888643 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.1148. Min Act: -0.0001

Data Index: 273451 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 3.7005. Min Range: -3.7005

Max Act: 2.8355. Min Act: -0.0000

Data Index: 145370 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 3.7005. Min Range: -3.7005

Max Act: 3.0997. Min Act: -0.0001

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 620