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

Dataset: The Pile

Neuron 1231 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: 4.7210. Min Range: -4.7210

Max Act: 4.7210. Min Act: -0.0000

Data Index: 1168492 (The Pile)

Max Activating Token Index: 965

Text #1

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.8393. Min Act: -0.0000

Data Index: 541872 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.7858. Min Act: -0.0000

Data Index: 725325 (The Pile)

Max Activating Token Index: 678

Text #3

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.4280. Min Act: -0.0000

Data Index: 1783887 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 4.7210. Min Range: -4.7210

Max Act: 4.0229. Min Act: -0.0000

Data Index: 166560 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.4603. Min Act: -0.0000

Data Index: 1953306 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.7247. Min Act: -0.0000

Data Index: 1997921 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.5936. Min Act: -0.0000

Data Index: 1695476 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.6999. Min Act: -0.0000

Data Index: 1253512 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.4081. Min Act: -0.0000

Data Index: 1319297 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.5037. Min Act: -0.0000

Data Index: 1391035 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.3821. Min Act: -0.0000

Data Index: 1571128 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.3632. Min Act: -0.0000

Data Index: 242705 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.6535. Min Act: -0.0000

Data Index: 293421 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.4661. Min Act: -0.0000

Data Index: 574542 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.5702. Min Act: -0.0000

Data Index: 1616251 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.9452. Min Act: -0.0000

Data Index: 1013073 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.1350. Min Act: -0.0000

Data Index: 328742 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.0139. Min Act: -0.0000

Data Index: 364526 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 4.7210. Min Range: -4.7210

Max Act: 3.4189. Min Act: -0.0000

Data Index: 1654227 (The Pile)

Max Activating Token Index: 447