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

Dataset: The Pile

Neuron 2698 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: 0.1938. Min Range: -0.1938

Max Act: 0.1779. Min Act: -0.0000

Data Index: 406808 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1812658 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1742. Min Act: -0.0000

Data Index: 8049 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1637. Min Act: -0.0000

Data Index: 632830 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1551. Min Act: -0.0000

Data Index: 854230 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1997851 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1124517 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1326. Min Act: -0.0000

Data Index: 313566 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1442. Min Act: -0.0000

Data Index: 324381 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1390. Min Act: -0.0000

Data Index: 695379 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1858999 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1435. Min Act: -0.0000

Data Index: 802208 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1380. Min Act: -0.0000

Data Index: 518972 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1452. Min Act: -0.0000

Data Index: 163108 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1288. Min Act: -0.0000

Data Index: 235325 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1456. Min Act: -0.0000

Data Index: 329844 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1265. Min Act: -0.0000

Data Index: 593357 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1460082 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1057144 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1254. Min Act: -0.0000

Data Index: 618905 (The Pile)

Max Activating Token Index: 253