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

Dataset: The Pile

Neuron 4062 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.3376. Min Act: -0.0000

Data Index: 1579422 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2390. Min Act: -0.0000

Data Index: 1093909 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1157. Min Act: -0.0000

Data Index: 1751409 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2216. Min Act: -0.0000

Data Index: 591273 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.9810. Min Act: -0.0000

Data Index: 396959 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.8609. Min Act: -0.0000

Data Index: 1807847 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7268. Min Act: -0.0000

Data Index: 1114392 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1402. Min Act: -0.0000

Data Index: 982536 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.8045. Min Act: -0.0000

Data Index: 227742 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.6495. Min Act: -0.0000

Data Index: 765904 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7782. Min Act: -0.0000

Data Index: 13043 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7855. Min Act: -0.0000

Data Index: 950651 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7407. Min Act: -0.0000

Data Index: 1216412 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7428. Min Act: -0.0000

Data Index: 996200 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7428. Min Act: -0.0000

Data Index: 1611486 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.5899. Min Act: -0.0000

Data Index: 827896 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.7232. Min Act: -0.0000

Data Index: 1417883 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.8624. Min Act: -0.0000

Data Index: 1001835 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.5733. Min Act: -0.0000

Data Index: 295425 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 3.3376. Min Range: -3.3376

Max Act: 2.5591. Min Act: -0.0000

Data Index: 851291 (The Pile)

Max Activating Token Index: 651