Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 568 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0005

Data Index: 868888 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0708. Min Act: -0.0005

Data Index: 415185 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0710. Min Act: -0.0005

Data Index: 968060 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0720. Min Act: -0.0005

Data Index: 847931 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0666. Min Act: -0.0005

Data Index: 614121 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0658. Min Act: -0.0005

Data Index: 509676 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0646. Min Act: -0.0005

Data Index: 342523 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0657. Min Act: -0.0005

Data Index: 230584 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0630. Min Act: -0.0005

Data Index: 661801 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0640. Min Act: -0.0005

Data Index: 1059170 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0650. Min Act: -0.0005

Data Index: 675327 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0648. Min Act: -0.0005

Data Index: 686474 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0649. Min Act: -0.0005

Data Index: 1149320 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0648. Min Act: -0.0005

Data Index: 1254029 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0646. Min Act: -0.0005

Data Index: 819580 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0653. Min Act: -0.0005

Data Index: 746968 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0640. Min Act: -0.0005

Data Index: 184073 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0632. Min Act: -0.0005

Data Index: 883867 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0617. Min Act: -0.0005

Data Index: 396306 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0617. Min Act: -0.0005

Data Index: 956194 (C4 (Web Text))

Max Activating Token Index: 938