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

Dataset: The Pile

Neuron 1648 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: 0.5946. Min Range: -0.5946

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1304128 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1846416 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5579. Min Act: -0.0000

Data Index: 714621 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1026410 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5465. Min Act: -0.0000

Data Index: 309501 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1437556 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1317579 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1604770 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4882. Min Act: 0.0000

Data Index: 80066 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4859. Min Act: -0.0000

Data Index: 191161 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4625. Min Act: -0.0000

Data Index: 361951 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3370. Min Act: -0.0000

Data Index: 782422 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4447. Min Act: -0.0000

Data Index: 395709 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4451. Min Act: 0.0000

Data Index: 110675 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1608731 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4082. Min Act: -0.0000

Data Index: 900114 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4164. Min Act: -0.0000

Data Index: 676960 (The Pile)

Max Activating Token Index: 543

Text #17

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4216. Min Act: -0.0000

Data Index: 610868 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1606523 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1610598 (The Pile)

Max Activating Token Index: 270