Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 716 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0755. Min Act: -0.0006

Data Index: 158125 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0651. Min Act: -0.0006

Data Index: 292901 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0646. Min Act: -0.0006

Data Index: 40765 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0645. Min Act: -0.0006

Data Index: 1026985 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0704. Min Act: -0.0006

Data Index: 601516 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0635. Min Act: -0.0006

Data Index: 1263469 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0728. Min Act: -0.0006

Data Index: 489569 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0698. Min Act: -0.0006

Data Index: 1107520 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0556. Min Act: -0.0006

Data Index: 204403 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0708. Min Act: -0.0006

Data Index: 389924 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0567. Min Act: -0.0006

Data Index: 938580 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0559. Min Act: -0.0006

Data Index: 1266001 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0569. Min Act: -0.0006

Data Index: 1284833 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0636. Min Act: -0.0006

Data Index: 451236 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0539. Min Act: -0.0006

Data Index: 1285175 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0624. Min Act: -0.0006

Data Index: 56781 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0612. Min Act: -0.0006

Data Index: 159656 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0671. Min Act: -0.0006

Data Index: 822030 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0637. Min Act: -0.0006

Data Index: 588690 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0632. Min Act: -0.0006

Data Index: 726540 (C4 (Web Text))

Max Activating Token Index: 666