Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4293 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.1112. Min Range: -2.1112
Max Act: 2.1112. Min Act: -0.0000
Data Index: 1222454 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1112. Min Range: -2.1112
Max Act: 2.0438. Min Act: -0.0000
Data Index: 441442 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1112. Min Range: -2.1112
Max Act: 2.0392. Min Act: -0.0000
Data Index: 887014 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.9923. Min Act: -0.0000
Data Index: 770632 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.9183. Min Act: -0.0000
Data Index: 521678 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.6343. Min Act: -0.0000
Data Index: 185008 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.7938. Min Act: -0.0000
Data Index: 914340 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.8592. Min Act: -0.0000
Data Index: 75339 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.8774. Min Act: -0.0000
Data Index: 1425609 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.7332. Min Act: -0.0000
Data Index: 1256879 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.7326. Min Act: -0.0000
Data Index: 269130 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.7620. Min Act: -0.0000
Data Index: 656991 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.6812. Min Act: -0.0000
Data Index: 1979218 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.8144. Min Act: -0.0000
Data Index: 327832 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.5516. Min Act: -0.0000
Data Index: 347409 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.7701. Min Act: -0.0000
Data Index: 736017 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.6051. Min Act: -0.0000
Data Index: 1695448 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.6206. Min Act: -0.0000
Data Index: 983237 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.6455. Min Act: -0.0000
Data Index: 1793578 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1112. Min Range: -2.1112
Max Act: 1.5859. Min Act: -0.0000
Data Index: 1216503 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19