Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1044. Min Act: -0.0000

Data Index: 159717 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1119897 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.0577. Min Act: -0.0000

Data Index: 170445 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1255230 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8819. Min Act: -0.0000

Data Index: 285269 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9125. Min Act: -0.0000

Data Index: 98502 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9004. Min Act: -0.0000

Data Index: 447665 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8569. Min Act: -0.0000

Data Index: 814513 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1262429 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1314481 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7785. Min Act: -0.0000

Data Index: 674284 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8303. Min Act: -0.0000

Data Index: 283182 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1449199 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1492124 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7567. Min Act: -0.0000

Data Index: 333241 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1352453 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1611203 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7797. Min Act: -0.0000

Data Index: 652176 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7149. Min Act: -0.0000

Data Index: 302679 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.7110. Min Act: -0.0000

Data Index: 274768 (The Pile)

Max Activating Token Index: 170