Model: None
Dataset: The Pile
Neuron 3591 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.6383. Min Act: -0.1700
Data Index: 9267534 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.6070. Min Act: -0.1700
Data Index: 10070619 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.5133. Min Act: -0.1700
Data Index: 332555 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4820. Min Act: -0.1700
Data Index: 965720 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4820. Min Act: -0.1700
Data Index: 10703192 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4820. Min Act: -0.1700
Data Index: 10661395 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4820. Min Act: -0.1700
Data Index: 9988870 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 696927 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 152100 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 7591524 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 311578 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 3442993 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4508. Min Act: -0.1700
Data Index: 6729228 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4195. Min Act: -0.1700
Data Index: 8271377 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4195. Min Act: -0.1700
Data Index: 5872227 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4195. Min Act: -0.1700
Data Index: 10020530 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.4195. Min Act: -0.1700
Data Index: 629576 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.3883. Min Act: -0.1700
Data Index: 5925841 (The Pile)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.3883. Min Act: -0.1700
Data Index: 1953352 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6383. Min Range: -5.6383
Max Act: 5.3883. Min Act: -0.1700
Data Index: 4421948 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19