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

Dataset: The Pile

Neuron 789 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: 3.6406. Min Range: -3.6406

Max Act: 3.6406. Min Act: -0.0000

Data Index: 40606 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3969. Min Act: -0.0000

Data Index: 1274717 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.9489. Min Act: -0.0000

Data Index: 1135169 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0950. Min Act: -0.0000

Data Index: 1845395 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.3084. Min Act: -0.0000

Data Index: 42527 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0066. Min Act: -0.0000

Data Index: 86600 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0126. Min Act: -0.0000

Data Index: 1267699 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.1337. Min Act: -0.0000

Data Index: 1807947 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.8648. Min Act: -0.0000

Data Index: 198409 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.9950. Min Act: -0.0000

Data Index: 938935 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.9733. Min Act: -0.0000

Data Index: 268365 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.5140. Min Act: -0.0000

Data Index: 1838711 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.5220. Min Act: -0.0000

Data Index: 444324 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.7335. Min Act: -0.0000

Data Index: 1106759 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.9941. Min Act: -0.0000

Data Index: 1903357 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.4876. Min Act: -0.0000

Data Index: 310375 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.5484. Min Act: -0.0000

Data Index: 514786 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.5414. Min Act: -0.0000

Data Index: 383886 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.4548. Min Act: -0.0000

Data Index: 783749 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.6318. Min Act: -0.0000

Data Index: 706488 (The Pile)

Max Activating Token Index: 305