Model: None
Dataset: The Pile
Neuron 707 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 26803 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 34944 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 33766 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 33687 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1699
Data Index: 33382 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 33208 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 31955 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 31150 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 30290 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 30240 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 2368 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 26658 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 25272 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 21993 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 16050 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 14936 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 12671 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 7609 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1700
Data Index: 1164 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7720. Min Range: -1.7720
Max Act: 1.7720. Min Act: -0.1699
Data Index: 4212 (The Pile)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19