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

Dataset: The Pile

Neuron 2591 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.9113. Min Act: -0.0000

Data Index: 630430 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.9123. Min Act: -0.0000

Data Index: 678090 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1286114 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8345. Min Act: -0.0000

Data Index: 395286 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1424404 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8479. Min Act: -0.0000

Data Index: 302135 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8261. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1828516 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8311. Min Act: -0.0000

Data Index: 367060 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1447070 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7809. Min Act: -0.0000

Data Index: 598881 (The Pile)

Max Activating Token Index: 360

Text #13

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1319311 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1742703 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1878118 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1622748 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8026. Min Act: -0.0000

Data Index: 468312 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1533082 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7401. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 669