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

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

Neuron 743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.1638. Min Act: -0.0001

Data Index: 1151293 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.2470. Min Act: -0.0001

Data Index: 762268 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.1937. Min Act: -0.0001

Data Index: 330264 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.1332. Min Act: -0.0001

Data Index: 1567188 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.1949. Min Act: -0.0001

Data Index: 1032468 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.0562. Min Act: -0.0001

Data Index: 1131936 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.0706. Min Act: -0.0001

Data Index: 1312957 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9862. Min Act: -0.0001

Data Index: 1175222 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9690. Min Act: -0.0001

Data Index: 586514 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.2470. Min Range: -1.2470

Max Act: 1.0325. Min Act: -0.0001

Data Index: 723008 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9892. Min Act: -0.0001

Data Index: 609552 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9780. Min Act: -0.0001

Data Index: 38148 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1383424 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9872. Min Act: -0.0001

Data Index: 1092745 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1049537 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9609. Min Act: -0.0001

Data Index: 1295653 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9175. Min Act: -0.0001

Data Index: 547990 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1052589 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9394. Min Act: -0.0001

Data Index: 371092 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 1.2470. Min Range: -1.2470

Max Act: 0.9153. Min Act: -0.0001

Data Index: 207358 (C4 (Web Text))

Max Activating Token Index: 429