Model: None
Dataset: The Pile
Neuron 715 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5533. Min Act: -0.1700
Data Index: 4848484 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5694. Min Act: -0.1700
Data Index: 3672106 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5694. Min Act: -0.1700
Data Index: 3731966 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5372. Min Act: -0.1700
Data Index: 786432 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5855. Min Act: -0.1700
Data Index: 9019727 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5372. Min Act: -0.1700
Data Index: 3854314 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5372. Min Act: -0.1700
Data Index: 9321603 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5372. Min Act: -0.1700
Data Index: 9858627 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5533. Min Act: -0.1700
Data Index: 6500530 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5372. Min Act: -0.1700
Data Index: 4401824 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5048. Min Act: -0.1700
Data Index: 5032617 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5210. Min Act: -0.1700
Data Index: 4944210 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5048. Min Act: -0.1700
Data Index: 8765824 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5048. Min Act: -0.1700
Data Index: 6190964 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5210. Min Act: -0.1700
Data Index: 5962955 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5210. Min Act: -0.1700
Data Index: 3533814 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5048. Min Act: -0.1700
Data Index: 2831351 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.4724. Min Act: -0.1700
Data Index: 4169687 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5048. Min Act: -0.1700
Data Index: 8475339 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5855. Min Range: -2.5855
Max Act: 2.5048. Min Act: -0.1700
Data Index: 833441 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19