Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 590 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2829. Min Act: -0.0001

Data Index: 853268 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2717. Min Act: -0.0001

Data Index: 509421 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2770. Min Act: -0.0001

Data Index: 137933 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2789. Min Act: -0.0001

Data Index: 107990 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2643. Min Act: -0.0001

Data Index: 786735 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2726. Min Act: -0.0001

Data Index: 1021091 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2667. Min Act: -0.0001

Data Index: 984029 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2625. Min Act: -0.0001

Data Index: 792889 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2696. Min Act: -0.0001

Data Index: 97708 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2516. Min Act: -0.0001

Data Index: 521067 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1125600 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2561. Min Act: -0.0001

Data Index: 849367 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2666. Min Act: -0.0001

Data Index: 500960 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2580. Min Act: -0.0001

Data Index: 45688 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2576. Min Act: -0.0001

Data Index: 918403 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2577. Min Act: -0.0001

Data Index: 599625 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2398. Min Act: -0.0001

Data Index: 365352 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2485. Min Act: -0.0001

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2721. Min Act: -0.0001

Data Index: 500476 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.2829. Min Range: -0.2829

Max Act: 0.2519. Min Act: -0.0001

Data Index: 727481 (C4 (Web Text))

Max Activating Token Index: 112