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

Dataset: The Pile

Neuron 4458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.6158. Min Act: -0.0000

Data Index: 1365481 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.7298. Min Act: -0.0000

Data Index: 828482 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.2444. Min Act: -0.0000

Data Index: 104592 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.6702. Min Act: -0.0000

Data Index: 447487 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.2798. Min Act: -0.0000

Data Index: 212666 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.9796. Min Act: -0.0000

Data Index: 1258115 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.2669. Min Act: -0.0000

Data Index: 1934615 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.5715. Min Act: -0.0000

Data Index: 893879 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.9387. Min Act: -0.0000

Data Index: 929678 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.2074. Min Act: -0.0000

Data Index: 1233272 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.9932. Min Act: -0.0000

Data Index: 1230869 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.8692. Min Act: -0.0000

Data Index: 291851 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.1860. Min Act: -0.0000

Data Index: 31969 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.9663. Min Act: -0.0000

Data Index: 1225010 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.8451. Min Act: -0.0000

Data Index: 1328703 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 3.7298. Min Range: -3.7298

Max Act: 3.3515. Min Act: -0.0000

Data Index: 825203 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.8650. Min Act: -0.0000

Data Index: 1608881 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.8267. Min Act: -0.0000

Data Index: 641945 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.5611. Min Act: -0.0000

Data Index: 830233 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 3.7298. Min Range: -3.7298

Max Act: 2.9078. Min Act: -0.0000

Data Index: 545298 (The Pile)

Max Activating Token Index: 430