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

Dataset: The Pile

Neuron 2628 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.6444. Min Act: -0.0000

Data Index: 118680 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5258. Min Act: -0.0000

Data Index: 326988 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4816. Min Act: -0.0000

Data Index: 224138 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4907. Min Act: -0.0000

Data Index: 376972 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1526018 (The Pile)

Max Activating Token Index: 785

Text #5

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1416608 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1150384 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1673897 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1091635 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1790231 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4532. Min Act: -0.0000

Data Index: 766620 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5546. Min Act: -0.0000

Data Index: 71192 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4997. Min Act: -0.0000

Data Index: 740282 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4655. Min Act: -0.0000

Data Index: 429466 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4603. Min Act: -0.0000

Data Index: 12487 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1384500 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4388. Min Act: -0.0000

Data Index: 139347 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1968788 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4475. Min Act: -0.0000

Data Index: 76009 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1923389 (The Pile)

Max Activating Token Index: 963