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

Dataset: The Pile

Neuron 2874 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5852. Min Act: -0.0000

Data Index: 604776 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6452. Min Act: -0.0000

Data Index: 120562 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5966. Min Act: -0.0000

Data Index: 652573 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5498. Min Act: -0.0000

Data Index: 737128 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1424258 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5035. Min Act: -0.0000

Data Index: 222741 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5223. Min Act: -0.0000

Data Index: 3031 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1332689 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4594. Min Act: -0.0000

Data Index: 162915 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4523. Min Act: -0.0000

Data Index: 325629 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1218503 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1512041 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1721116 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1298430 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4268. Min Act: -0.0000

Data Index: 647457 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4276. Min Act: -0.0000

Data Index: 186708 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4274. Min Act: -0.0000

Data Index: 571747 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1554677 (The Pile)

Max Activating Token Index: 670

Text #18

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1158502 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1762963 (The Pile)

Max Activating Token Index: 787