Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 425 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.7200. Min Act: -0.0001

Data Index: 366704 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.5490. Min Act: -0.0001

Data Index: 550155 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.4517. Min Act: -0.0001

Data Index: 1025419 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.4312. Min Act: -0.0001

Data Index: 1191503 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3895. Min Act: -0.0001

Data Index: 634396 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3645. Min Act: -0.0001

Data Index: 1087105 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3749. Min Act: -0.0001

Data Index: 535700 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3926. Min Act: -0.0001

Data Index: 137555 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3290. Min Act: -0.0001

Data Index: 585952 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3220. Min Act: -0.0001

Data Index: 396274 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3202. Min Act: -0.0002

Data Index: 431464 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2462. Min Act: -0.0001

Data Index: 764514 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3491. Min Act: -0.0001

Data Index: 1313534 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2812. Min Act: -0.0001

Data Index: 1318573 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2352. Min Act: -0.0002

Data Index: 946093 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2778. Min Act: -0.0001

Data Index: 517207 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2696. Min Act: -0.0001

Data Index: 961600 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2730. Min Act: -0.0001

Data Index: 1142604 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2333. Min Act: -0.0001

Data Index: 1117109 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2493. Min Act: -0.0001

Data Index: 962936 (C4 (Web Text))

Max Activating Token Index: 195