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

Dataset: The Pile

Neuron 1783 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: 5.0083. Min Range: -5.0083

Max Act: 5.0083. Min Act: -0.0000

Data Index: 1943491 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.6674. Min Act: -0.0000

Data Index: 54404 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.8277. Min Act: -0.0000

Data Index: 1349931 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.9698. Min Act: -0.0000

Data Index: 1184383 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.4266. Min Act: -0.0000

Data Index: 468252 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.5409. Min Act: -0.0000

Data Index: 786952 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.9446. Min Act: -0.0000

Data Index: 1048794 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.4335. Min Act: -0.0000

Data Index: 515039 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.2599. Min Act: -0.0000

Data Index: 463643 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.5048. Min Act: -0.0000

Data Index: 248704 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.0541. Min Act: -0.0000

Data Index: 625255 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.8732. Min Act: -0.0000

Data Index: 1388251 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.0428. Min Act: -0.0000

Data Index: 409216 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 5.0083. Min Range: -5.0083

Max Act: 4.0358. Min Act: -0.0000

Data Index: 1368120 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.9362. Min Act: -0.0000

Data Index: 868163 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.8056. Min Act: -0.0000

Data Index: 1363621 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.4968. Min Act: -0.0000

Data Index: 1422098 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.3220. Min Act: -0.0000

Data Index: 922191 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.6224. Min Act: -0.0000

Data Index: 115466 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 5.0083. Min Range: -5.0083

Max Act: 3.4419. Min Act: -0.0000

Data Index: 1019109 (The Pile)

Max Activating Token Index: 101