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

Dataset: The Pile

Neuron 4750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3937. Min Range: -7.3937

Max Act: 7.0766. Min Act: -0.0000

Data Index: 841489 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 7.3937. Min Range: -7.3937

Max Act: 7.3937. Min Act: -0.0000

Data Index: 39180 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.9483. Min Act: -0.0000

Data Index: 1600573 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.7183. Min Act: -0.0000

Data Index: 1357329 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 7.3937. Min Range: -7.3937

Max Act: 5.9580. Min Act: -0.0000

Data Index: 578010 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1213. Min Act: -0.0000

Data Index: 475854 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1058. Min Act: -0.0000

Data Index: 1476641 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1702. Min Act: -0.0000

Data Index: 1948699 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 7.3937. Min Range: -7.3937

Max Act: 5.9829. Min Act: -0.0000

Data Index: 1455938 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1297. Min Act: -0.0000

Data Index: 204822 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1323. Min Act: -0.0000

Data Index: 1335690 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.3350. Min Act: -0.0000

Data Index: 478608 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 7.3937. Min Range: -7.3937

Max Act: 5.8902. Min Act: -0.0000

Data Index: 1379309 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 7.3937. Min Range: -7.3937

Max Act: 5.7337. Min Act: -0.0000

Data Index: 600816 (The Pile)

Max Activating Token Index: 1001

Text #14

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1011. Min Act: -0.0000

Data Index: 1239006 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.1100. Min Act: -0.0000

Data Index: 434855 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 7.3937. Min Range: -7.3937

Max Act: 5.9129. Min Act: -0.0000

Data Index: 80949 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.2509. Min Act: -0.0000

Data Index: 537636 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 7.3937. Min Range: -7.3937

Max Act: 6.0423. Min Act: -0.0000

Data Index: 380220 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 7.3937. Min Range: -7.3937

Max Act: 5.9800. Min Act: -0.0000

Data Index: 1139873 (The Pile)

Max Activating Token Index: 439