Model: None
Dataset: The Pile
Neuron 1153 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.9737. Min Act: -0.1700
Data Index: 5160714 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.9737. Min Act: -0.1700
Data Index: 3136409 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.9737. Min Act: -0.1700
Data Index: 10117315 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.9103. Min Act: -0.1700
Data Index: 5895367 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.9262. Min Act: -0.1700
Data Index: 9345150 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8945. Min Act: -0.1700
Data Index: 3488813 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8945. Min Act: -0.1700
Data Index: 4279189 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1700
Data Index: 4028144 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8945. Min Act: -0.1700
Data Index: 2511598 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1700
Data Index: 2037623 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1700
Data Index: 9577453 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8945. Min Act: -0.1700
Data Index: 5459250 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1699
Data Index: 4363663 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1700
Data Index: 8216838 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8468. Min Act: -0.1700
Data Index: 6622726 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8627. Min Act: -0.1700
Data Index: 3671542 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1700
Data Index: 7302727 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8627. Min Act: -0.1700
Data Index: 7450634 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8786. Min Act: -0.1699
Data Index: 7777502 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9737. Min Range: -2.9737
Max Act: 2.8468. Min Act: -0.1700
Data Index: 2476915 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19