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

Dataset: The Pile

Neuron 3921 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0000

Data Index: 893981 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1117491 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1900541 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0266. Min Act: -0.0000

Data Index: 1536018 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0261. Min Act: -0.0000

Data Index: 155015 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0259. Min Act: 0.0000

Data Index: 1204638 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1274789 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0257. Min Act: -0.0000

Data Index: 107254 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0255. Min Act: -0.0000

Data Index: 122368 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1433837 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0263. Min Act: -0.0000

Data Index: 763739 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0251. Min Act: 0.0000

Data Index: 281404 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0260. Min Act: -0.0000

Data Index: 375514 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0252. Min Act: -0.0000

Data Index: 15036 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1758536 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1015595 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0245. Min Act: -0.0000

Data Index: 845954 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1356938 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1264422 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1807359 (The Pile)

Max Activating Token Index: 500