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

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

Neuron 4100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.6623. Min Act: -0.0000

Data Index: 336743 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3147. Min Act: -0.0000

Data Index: 289002 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2399. Min Act: -0.0000

Data Index: 217374 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3437. Min Act: -0.0000

Data Index: 443937 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2815. Min Act: -0.0000

Data Index: 36493 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2341. Min Act: -0.0000

Data Index: 784763 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2333. Min Act: -0.0000

Data Index: 546740 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2166. Min Act: -0.0000

Data Index: 504329 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1288427 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2266. Min Act: 0.0000

Data Index: 248388 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1181863 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1232028 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1091893 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1766. Min Act: -0.0000

Data Index: 629806 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2008. Min Act: -0.0000

Data Index: 993304 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1924. Min Act: 0.0000

Data Index: 884764 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1586. Min Act: -0.0000

Data Index: 501071 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1113247 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1496. Min Act: -0.0000

Data Index: 882031 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.1465. Min Act: -0.0000

Data Index: 466650 (C4 (Web Text))

Max Activating Token Index: 586