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

Dataset: The Pile

Neuron 375 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1455542 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7922. Min Act: 0.0000

Data Index: 1988699 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7066. Min Act: -0.0000

Data Index: 156070 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7295. Min Act: -0.0000

Data Index: 123844 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7292. Min Act: -0.0000

Data Index: 611729 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7264. Min Act: -0.0000

Data Index: 237538 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1642479 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7510. Min Act: -0.0000

Data Index: 87053 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1034134 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7002. Min Act: -0.0000

Data Index: 162093 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1395885 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6710. Min Act: -0.0000

Data Index: 429854 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6677. Min Act: -0.0000

Data Index: 570137 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1953056 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1785389 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6428. Min Act: -0.0000

Data Index: 459744 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1096036 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1194365 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1287771 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1550405 (The Pile)

Max Activating Token Index: 632