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

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

Neuron 789 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: 1.3383. Min Range: -1.3383

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1295474 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.3383. Min Act: -0.0000

Data Index: 1200368 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2968. Min Act: -0.0000

Data Index: 98116 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1315975 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1325. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2122. Min Act: -0.0000

Data Index: 700969 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2091. Min Act: -0.0000

Data Index: 617500 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2808. Min Act: -0.0000

Data Index: 685884 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2027. Min Act: -0.0000

Data Index: 553640 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1262091 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1670. Min Act: -0.0000

Data Index: 280919 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1152709 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1064151 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1030090 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1721. Min Act: -0.0000

Data Index: 470914 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1012. Min Act: -0.0000

Data Index: 2166 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0906. Min Act: -0.0000

Data Index: 396872 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1271. Min Act: -0.0000

Data Index: 240353 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1076. Min Act: -0.0000

Data Index: 6143 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9933. Min Act: -0.0000

Data Index: 825110 (C4 (Web Text))

Max Activating Token Index: 725