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

Dataset: The Pile

Neuron 1786 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.5289. Min Act: -0.0000

Data Index: 1358913 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.5236. Min Act: -0.0000

Data Index: 1405701 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.2451. Min Act: -0.0000

Data Index: 394480 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.1268. Min Act: -0.0000

Data Index: 1043526 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.0657. Min Act: -0.0000

Data Index: 871367 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.1893. Min Act: -0.0000

Data Index: 318340 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.0358. Min Act: -0.0000

Data Index: 868907 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1502570 (The Pile)

Max Activating Token Index: 671

Text #8

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.9745. Min Act: -0.0000

Data Index: 1557616 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.0511. Min Act: -0.0000

Data Index: 663156 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.9526. Min Act: -0.0000

Data Index: 644155 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.8405. Min Act: -0.0000

Data Index: 488528 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.0287. Min Act: -0.0001

Data Index: 1773769 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 3.5289. Min Range: -3.5289

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1001045 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.8484. Min Act: -0.0000

Data Index: 557737 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.8170. Min Act: -0.0000

Data Index: 1460971 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.7874. Min Act: -0.0000

Data Index: 867951 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.7604. Min Act: -0.0000

Data Index: 753568 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1023828 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 3.5289. Min Range: -3.5289

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1339948 (The Pile)

Max Activating Token Index: 60