Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 2 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0919. Min Act: -0.0004
Data Index: 122317 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0886. Min Act: -0.0004
Data Index: 922464 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0882. Min Act: -0.0004
Data Index: 1730177 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0788. Min Act: -0.0003
Data Index: 651248 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0762. Min Act: -0.0004
Data Index: 1763163 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0781. Min Act: -0.0004
Data Index: 1545097 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0788. Min Act: -0.0003
Data Index: 853437 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0802. Min Act: -0.0004
Data Index: 1031271 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0766. Min Act: -0.0004
Data Index: 195986 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0775. Min Act: -0.0004
Data Index: 1948620 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0757. Min Act: -0.0004
Data Index: 1505394 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0763. Min Act: -0.0004
Data Index: 184105 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0692. Min Act: -0.0004
Data Index: 1143423 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0769. Min Act: -0.0004
Data Index: 1322211 (The Pile)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0738. Min Act: -0.0004
Data Index: 603892 (The Pile)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0707. Min Act: -0.0004
Data Index: 787984 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0703. Min Act: -0.0004
Data Index: 894842 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0701. Min Act: -0.0004
Data Index: 451298 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0695. Min Act: -0.0004
Data Index: 309826 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0919. Min Range: -0.0919
Max Act: 0.0720. Min Act: -0.0004
Data Index: 1886550 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19