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

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

Neuron 3638 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.7352. Min Act: -0.0000

Data Index: 827418 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.2457. Min Act: -0.0000

Data Index: 288295 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.2554. Min Act: -0.0000

Data Index: 260371 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1104566 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1037695 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.2033. Min Act: -0.0000

Data Index: 16046 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1215218 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1248496 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1772. Min Act: -0.0000

Data Index: 574986 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1696. Min Act: -0.0000

Data Index: 348696 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1647. Min Act: -0.0000

Data Index: 499770 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1277. Min Act: -0.0000

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1543. Min Act: -0.0000

Data Index: 445014 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.0422. Min Act: -0.0000

Data Index: 472349 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.0725. Min Act: -0.0000

Data Index: 767025 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1057. Min Act: -0.0000

Data Index: 368204 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1235. Min Act: -0.0000

Data Index: 12001 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1224. Min Act: -0.0000

Data Index: 792330 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1232117 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.7352. Min Range: -1.7352

Max Act: 1.0345. Min Act: -0.0000

Data Index: 717040 (C4 (Web Text))

Max Activating Token Index: 137