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

Dataset: The Pile

Neuron 3310 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: 1.4338. Min Range: -1.4338

Max Act: 1.3641. Min Act: -0.0000

Data Index: 84495 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1676988 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1642695 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.4338. Min Act: -0.0000

Data Index: 432394 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.3646. Min Act: -0.0000

Data Index: 512416 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.3287. Min Act: -0.0000

Data Index: 84879 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1221897 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.2667. Min Act: -0.0000

Data Index: 30629 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1577022 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1774225 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.1595. Min Act: -0.0000

Data Index: 613347 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1492278 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.1305. Min Act: -0.0000

Data Index: 254324 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1933889 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.0893. Min Act: -0.0000

Data Index: 714159 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.0355. Min Act: -0.0000

Data Index: 670334 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.0887. Min Act: -0.0000

Data Index: 289039 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1634203 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 1.4338. Min Range: -1.4338

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1920672 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 1.4338. Min Range: -1.4338

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1244236 (The Pile)

Max Activating Token Index: 133