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

Dataset: The Pile

Neuron 2378 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: 1.9952. Min Range: -1.9952

Max Act: 1.9952. Min Act: -0.0000

Data Index: 1759241 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.6792. Min Act: -0.0000

Data Index: 468023 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5564. Min Act: -0.0000

Data Index: 639901 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.6451. Min Act: -0.0000

Data Index: 415153 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.8096. Min Act: -0.0000

Data Index: 716629 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5442. Min Act: -0.0000

Data Index: 804856 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1990518 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1403422 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.7583. Min Act: -0.0000

Data Index: 1624492 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.5125. Min Act: -0.0000

Data Index: 180219 (The Pile)

Max Activating Token Index: 844

Text #10

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.6050. Min Act: -0.0000

Data Index: 293087 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4371. Min Act: -0.0000

Data Index: 618929 (The Pile)

Max Activating Token Index: 770

Text #12

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1006477 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4543. Min Act: -0.0000

Data Index: 755191 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1977852 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.3656. Min Act: -0.0000

Data Index: 207054 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1569863 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1886704 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1378463 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 1.9952. Min Range: -1.9952

Max Act: 1.4100. Min Act: -0.0000

Data Index: 1540436 (The Pile)

Max Activating Token Index: 487