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

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

Neuron 527 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: 0.3324. Min Range: -0.3324

Max Act: 0.3324. Min Act: -0.0005

Data Index: 319381 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2783. Min Act: -0.0005

Data Index: 511547 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2947. Min Act: -0.0005

Data Index: 561291 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2776. Min Act: -0.0005

Data Index: 1359303 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2832. Min Act: -0.0005

Data Index: 204475 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2689. Min Act: -0.0005

Data Index: 943128 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2779. Min Act: -0.0005

Data Index: 1225407 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2647. Min Act: -0.0005

Data Index: 1126777 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2722. Min Act: -0.0005

Data Index: 106584 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2906. Min Act: -0.0005

Data Index: 1333587 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2621. Min Act: -0.0005

Data Index: 719880 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2784. Min Act: -0.0005

Data Index: 1055954 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2672. Min Act: -0.0005

Data Index: 358220 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2595. Min Act: -0.0005

Data Index: 879967 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2662. Min Act: -0.0005

Data Index: 687992 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2654. Min Act: -0.0005

Data Index: 88879 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2642. Min Act: -0.0005

Data Index: 140882 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2628. Min Act: -0.0005

Data Index: 860844 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2600. Min Act: -0.0005

Data Index: 733139 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2599. Min Act: -0.0005

Data Index: 485929 (C4 (Web Text))

Max Activating Token Index: 800