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

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

Neuron 4734 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: 0.5366. Min Range: -0.5366

Max Act: 0.5366. Min Act: -0.0001

Data Index: 583464 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4821. Min Act: -0.0001

Data Index: 417857 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.5080. Min Act: -0.0001

Data Index: 1005439 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4759. Min Act: -0.0001

Data Index: 213212 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4209. Min Act: -0.0001

Data Index: 492405 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4091. Min Act: -0.0001

Data Index: 1034365 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3885. Min Act: -0.0001

Data Index: 418634 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3850. Min Act: -0.0001

Data Index: 518114 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3840. Min Act: -0.0001

Data Index: 804593 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1131869 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3805. Min Act: -0.0001

Data Index: 480403 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3814. Min Act: -0.0001

Data Index: 276754 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3836. Min Act: -0.0001

Data Index: 999514 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3562. Min Act: -0.0001

Data Index: 262857 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3581. Min Act: -0.0001

Data Index: 1268781 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3785. Min Act: -0.0001

Data Index: 397528 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3842. Min Act: -0.0001

Data Index: 549860 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4149. Min Act: -0.0001

Data Index: 318813 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1017817 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3683. Min Act: -0.0001

Data Index: 907607 (C4 (Web Text))

Max Activating Token Index: 455