Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 13 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.6885. Min Act: -0.0000
Data Index: 1101492 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.6863. Min Act: -0.0000
Data Index: 14421 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.7153. Min Act: -0.0000
Data Index: 1363800 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.5940. Min Act: -0.0000
Data Index: 253966 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.5850. Min Act: -0.0000
Data Index: 646448 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.5112. Min Act: -0.0000
Data Index: 1563743 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.4977. Min Act: -0.0000
Data Index: 1056171 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.4811. Min Act: -0.0000
Data Index: 1414068 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.5166. Min Act: -0.0000
Data Index: 402367 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.5632. Min Act: 0.0000
Data Index: 431437 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.4943. Min Act: -0.0000
Data Index: 866841 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.4487. Min Act: 0.0000
Data Index: 830611 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.5046. Min Act: -0.0000
Data Index: 858884 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.4304. Min Act: -0.0000
Data Index: 1513060 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.3553. Min Act: -0.0000
Data Index: 1545096 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.4222. Min Act: -0.0000
Data Index: 690269 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.3352. Min Act: -0.0000
Data Index: 1491008 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.3974. Min Act: -0.0000
Data Index: 742714 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.3519. Min Act: -0.0000
Data Index: 1173100 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7153. Min Range: -1.7153
Max Act: 1.3876. Min Act: -0.0000
Data Index: 745547 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19