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

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

Neuron 3744 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0606. Min Range: -2.0606

Max Act: 2.0606. Min Act: -0.0000

Data Index: 459447 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.6593. Min Act: -0.0000

Data Index: 803386 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.6567. Min Act: -0.0000

Data Index: 719880 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.6787. Min Act: -0.0000

Data Index: 634725 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.6367. Min Act: -0.0000

Data Index: 362525 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.4801. Min Act: -0.0000

Data Index: 942145 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3651. Min Act: -0.0000

Data Index: 605179 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.6003. Min Act: -0.0000

Data Index: 108145 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.4107. Min Act: -0.0000

Data Index: 282683 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1086045 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.4028. Min Act: -0.0000

Data Index: 1224571 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1321729 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3729. Min Act: -0.0000

Data Index: 983606 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1350486 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3395. Min Act: -0.0000

Data Index: 236805 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1273130 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3782. Min Act: -0.0000

Data Index: 13795 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1183880 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.3133. Min Act: -0.0000

Data Index: 987226 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 2.0606. Min Range: -2.0606

Max Act: 1.1475. Min Act: -0.0000

Data Index: 327923 (C4 (Web Text))

Max Activating Token Index: 761