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

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

Neuron 629 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3229. Min Act: -0.0001

Data Index: 1246397 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1044099 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3047. Min Act: -0.0001

Data Index: 35502 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2940. Min Act: 0.0001

Data Index: 936450 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2946. Min Act: -0.0001

Data Index: 421595 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2940. Min Act: -0.0001

Data Index: 173789 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2879. Min Act: -0.0001

Data Index: 315593 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2758. Min Act: -0.0001

Data Index: 105117 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2901. Min Act: 0.0001

Data Index: 354052 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1031288 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2939. Min Act: -0.0001

Data Index: 879081 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2800. Min Act: -0.0001

Data Index: 801871 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2781. Min Act: -0.0001

Data Index: 233579 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2664. Min Act: -0.0001

Data Index: 673611 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2639. Min Act: -0.0001

Data Index: 862632 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2604. Min Act: -0.0001

Data Index: 965250 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2628. Min Act: -0.0001

Data Index: 233919 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2578. Min Act: -0.0001

Data Index: 426121 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2582. Min Act: 0.0001

Data Index: 652923 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2573. Min Act: -0.0001

Data Index: 146709 (C4 (Web Text))

Max Activating Token Index: 143