Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2603 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2273. Min Act: -0.0001

Data Index: 943134 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2019. Min Act: -0.0001

Data Index: 86817 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1256975 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1983. Min Act: -0.0001

Data Index: 399545 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1170179 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1927. Min Act: -0.0001

Data Index: 255623 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1829. Min Act: -0.0001

Data Index: 1306189 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1784. Min Act: -0.0001

Data Index: 601972 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1829. Min Act: -0.0001

Data Index: 1006464 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1756. Min Act: -0.0001

Data Index: 615258 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1797. Min Act: -0.0001

Data Index: 479474 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1731. Min Act: -0.0001

Data Index: 938386 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1841. Min Act: -0.0001

Data Index: 792546 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1093165 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1632. Min Act: -0.0001

Data Index: 230870 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1576. Min Act: -0.0001

Data Index: 874686 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1515. Min Act: -0.0001

Data Index: 713367 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1497. Min Act: -0.0001

Data Index: 664364 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1522. Min Act: -0.0001

Data Index: 979156 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1330858 (C4 (Web Text))

Max Activating Token Index: 644