Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1870777 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8218. Min Act: -0.0000

Data Index: 473607 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.9744. Min Act: -0.0000

Data Index: 1875700 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1410197 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6420. Min Act: -0.0000

Data Index: 361718 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1785858 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1831316 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1591215 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6400. Min Act: -0.0000

Data Index: 162245 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1512828 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1006533 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.5964. Min Act: -0.0000

Data Index: 61731 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6329. Min Act: -0.0000

Data Index: 777568 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1200246 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1132158 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1576425 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1043673 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1766332 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1392669 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6010. Min Act: -0.0000

Data Index: 595459 (The Pile)

Max Activating Token Index: 999