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

Dataset: The Pile

Neuron 4940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.1935. Min Act: -0.0000

Data Index: 1285364 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1077476 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1182620 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1678945 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9943. Min Act: -0.0000

Data Index: 679517 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9305. Min Act: -0.0000

Data Index: 735284 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0019. Min Act: -0.0000

Data Index: 820854 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0549. Min Act: -0.0000

Data Index: 199395 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1948736 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 1.1935. Min Range: -1.1935

Max Act: 1.0785. Min Act: -0.0000

Data Index: 225959 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.6792. Min Act: -0.0000

Data Index: 921237 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9639. Min Act: -0.0000

Data Index: 237431 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9330. Min Act: -0.0000

Data Index: 457505 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8996. Min Act: -0.0000

Data Index: 934633 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1230182 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8628. Min Act: -0.0000

Data Index: 87803 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8439. Min Act: -0.0000

Data Index: 222363 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1359165 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1766163 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 1.1935. Min Range: -1.1935

Max Act: 0.8050. Min Act: -0.0000

Data Index: 963750 (The Pile)

Max Activating Token Index: 44