Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5336 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.7634. Min Act: -0.1700
Data Index: 396839 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.5759. Min Act: -0.1700
Data Index: 7622338 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.5759. Min Act: -0.1700
Data Index: 5065721 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.5134. Min Act: -0.1700
Data Index: 5932828 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.4509. Min Act: -0.1700
Data Index: 4725755 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.4509. Min Act: -0.1700
Data Index: 6957001 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.3884. Min Act: -0.1700
Data Index: 2287991 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.3259. Min Act: -0.1700
Data Index: 622075 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2634. Min Act: -0.1700
Data Index: 3427048 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 3887334 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 270302 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 734691 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 3609873 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.1384. Min Act: -0.1700
Data Index: 6507906 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 3411782 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 8341279 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 2531577 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.1384. Min Act: -0.1700
Data Index: 1648473 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.2009. Min Act: -0.1700
Data Index: 4609268 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7634. Min Range: -8.7634
Max Act: 8.1384. Min Act: -0.1700
Data Index: 4569986 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19