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

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

Neuron 1510 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5202. Min Act: -0.0000

Data Index: 654259 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3890. Min Act: -0.0000

Data Index: 238550 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3873. Min Act: -0.0000

Data Index: 660950 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1334686 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4153. Min Act: -0.0000

Data Index: 833541 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3755. Min Act: -0.0000

Data Index: 33341 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3447. Min Act: -0.0000

Data Index: 758343 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3342. Min Act: -0.0000

Data Index: 674847 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3450. Min Act: -0.0000

Data Index: 86085 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1205181 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2902. Min Act: -0.0000

Data Index: 118734 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1305485 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2985. Min Act: -0.0000

Data Index: 363542 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2688. Min Act: -0.0000

Data Index: 504920 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2848. Min Act: -0.0000

Data Index: 16425 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2944. Min Act: -0.0000

Data Index: 71199 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2823. Min Act: 0.0000

Data Index: 127240 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2852. Min Act: -0.0000

Data Index: 269609 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1193755 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.2779. Min Act: -0.0000

Data Index: 216639 (C4 (Web Text))

Max Activating Token Index: 388