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

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

Neuron 1975 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.4300. Min Act: -0.0001

Data Index: 854580 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1323708 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2720. Min Act: -0.0000

Data Index: 850686 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2432. Min Act: -0.0000

Data Index: 463121 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2585. Min Act: -0.0000

Data Index: 257072 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2351. Min Act: -0.0000

Data Index: 300646 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1995. Min Act: -0.0000

Data Index: 585902 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1098237 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1193776 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1901. Min Act: -0.0001

Data Index: 360357 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1983. Min Act: -0.0000

Data Index: 5970 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1461. Min Act: -0.0000

Data Index: 535450 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1159434 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1693. Min Act: -0.0001

Data Index: 1282778 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1757. Min Act: -0.0000

Data Index: 127541 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1864. Min Act: -0.0001

Data Index: 1229558 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1770. Min Act: -0.0000

Data Index: 125895 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1496. Min Act: -0.0000

Data Index: 100888 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1356. Min Act: -0.0001

Data Index: 465741 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.0815. Min Act: -0.0000

Data Index: 983950 (C4 (Web Text))

Max Activating Token Index: 628