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

Dataset: The Pile

Neuron 2728 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1823743 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6234. Min Act: -0.0000

Data Index: 718600 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5713. Min Act: -0.0000

Data Index: 928309 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1831445 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5560. Min Act: -0.0000

Data Index: 41921 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5513. Min Act: -0.0000

Data Index: 654036 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5460. Min Act: -0.0000

Data Index: 129469 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5397. Min Act: -0.0000

Data Index: 525652 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1813892 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1631817 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5672. Min Act: -0.0000

Data Index: 572820 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5684. Min Act: -0.0000

Data Index: 667600 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5365. Min Act: -0.0000

Data Index: 24922 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1304438 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1854287 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5063. Min Act: -0.0000

Data Index: 643931 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4903. Min Act: -0.0000

Data Index: 459512 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1135300 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4731. Min Act: -0.0000

Data Index: 96332 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5060. Min Act: -0.0000

Data Index: 589849 (The Pile)

Max Activating Token Index: 97