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

Dataset: The Pile

Neuron 1257 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5289. Min Act: -0.0000

Data Index: 815845 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1805587 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5764. Min Act: -0.0000

Data Index: 51225 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1308352 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5015. Min Act: -0.0000

Data Index: 462367 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4648. Min Act: -0.0000

Data Index: 28355 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1277377 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4769. Min Act: -0.0000

Data Index: 953754 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1444864 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1664783 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1878240 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1446994 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4602. Min Act: -0.0000

Data Index: 989494 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1984480 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1283200 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1242482 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4199. Min Act: -0.0000

Data Index: 622509 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1123963 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1355769 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4607. Min Act: -0.0000

Data Index: 375369 (The Pile)

Max Activating Token Index: 216