Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3888. Min Act: -0.0000

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3508. Min Act: -0.0000

Data Index: 739710 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3690. Min Act: -0.0000

Data Index: 354195 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3313. Min Act: -0.0000

Data Index: 885560 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3110. Min Act: -0.0000

Data Index: 877060 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2889. Min Act: -0.0000

Data Index: 222808 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2932. Min Act: -0.0000

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1174392 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2902. Min Act: -0.0000

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2802. Min Act: -0.0000

Data Index: 216265 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2779. Min Act: -0.0000

Data Index: 182004 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2616. Min Act: -0.0000

Data Index: 457074 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2729. Min Act: -0.0000

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2772. Min Act: -0.0000

Data Index: 410019 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2616. Min Act: -0.0000

Data Index: 55104 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2617. Min Act: -0.0000

Data Index: 332319 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1324357 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2992. Min Act: -0.0000

Data Index: 583298 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2794. Min Act: -0.0000

Data Index: 296599 (C4 (Web Text))

Max Activating Token Index: 639