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

Dataset: The Pile

Neuron 4900 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.3289. Min Act: -0.0000

Data Index: 106597 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2414. Min Act: -0.0000

Data Index: 1268419 (The Pile)

Max Activating Token Index: 549

Text #2

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1912. Min Act: -0.0000

Data Index: 582127 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1514494 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1592. Min Act: -0.0000

Data Index: 857022 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1802397 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.9722. Min Act: -0.0000

Data Index: 361992 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1209392 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.9925. Min Act: -0.0000

Data Index: 867348 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 1.3289. Min Range: -1.3289

Max Act: 1.0399. Min Act: -0.0000

Data Index: 1904067 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1193022 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.9954. Min Act: -0.0000

Data Index: 569836 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1032710 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.8700. Min Act: -0.0000

Data Index: 974576 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1962252 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1009601 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1344128 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.8348. Min Act: -0.0000

Data Index: 378331 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1736436 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.3289. Min Range: -1.3289

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1140896 (The Pile)

Max Activating Token Index: 642