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

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

Neuron 4041 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: 1.2497. Min Range: -1.2497

Max Act: 1.2497. Min Act: -0.0000

Data Index: 360550 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.1697. Min Act: -0.0000

Data Index: 442449 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0641. Min Act: -0.0000

Data Index: 130898 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0547. Min Act: -0.0000

Data Index: 595298 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9963. Min Act: -0.0000

Data Index: 384546 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.7609. Min Act: -0.0000

Data Index: 921877 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.7058. Min Act: -0.0000

Data Index: 759548 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6347. Min Act: -0.0000

Data Index: 821437 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5990. Min Act: -0.0000

Data Index: 638914 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6097. Min Act: -0.0000

Data Index: 204890 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1076958 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5515. Min Act: -0.0000

Data Index: 399623 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5259. Min Act: -0.0000

Data Index: 572453 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5151. Min Act: -0.0000

Data Index: 294203 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5310. Min Act: -0.0000

Data Index: 856803 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5065. Min Act: -0.0000

Data Index: 625778 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5091. Min Act: -0.0000

Data Index: 119489 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1292753 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.4813. Min Act: -0.0000

Data Index: 174465 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1155199 (C4 (Web Text))

Max Activating Token Index: 841