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

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

Neuron 4327 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.6300. Min Act: -0.0001

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.5483. Min Act: -0.0000

Data Index: 993603 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1427727 (Python Code)

Max Activating Token Index: 844

Text #3

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4850. Min Act: -0.0000

Data Index: 277209 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1583613 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4219. Min Act: -0.0001

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1516108 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4315. Min Act: -0.0001

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4201. Min Act: -0.0000

Data Index: 795100 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1519894 (Python Code)

Max Activating Token Index: 688

Text #10

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1623689 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3725. Min Act: -0.0000

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1389172 (Python Code)

Max Activating Token Index: 405

Text #13

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1576543 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3988. Min Act: -0.0000

Data Index: 115604 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3959. Min Act: -0.0001

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1610465 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1591188 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3776. Min Act: -0.0001

Data Index: 1534363 (Python Code)

Max Activating Token Index: 691

Text #19

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1596572 (Python Code)

Max Activating Token Index: 34