Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0251. Min Range: -8.0251
Max Act: 8.0251. Min Act: -0.1700
Data Index: 8617055 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.6188. Min Act: -0.1700
Data Index: 7038769 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.4938. Min Act: -0.1700
Data Index: 8511840 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.3688. Min Act: -0.1700
Data Index: 2090082 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.3376. Min Act: -0.1700
Data Index: 4948855 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.2126. Min Act: -0.1700
Data Index: 5182499 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.1501. Min Act: -0.1700
Data Index: 4879585 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.1188. Min Act: -0.1700
Data Index: 4752941 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.1188. Min Act: -0.1700
Data Index: 384404 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0251. Min Range: -8.0251
Max Act: 7.0563. Min Act: -0.1700
Data Index: 6589292 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9626. Min Act: -0.1700
Data Index: 6804825 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9626. Min Act: -0.1700
Data Index: 2894044 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9626. Min Act: -0.1700
Data Index: 5585986 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9313. Min Act: -0.1700
Data Index: 7609194 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9001. Min Act: -0.1700
Data Index: 8418450 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9001. Min Act: -0.1700
Data Index: 4596089 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.9001. Min Act: -0.1700
Data Index: 7510319 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.8688. Min Act: -0.1700
Data Index: 5773672 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.8688. Min Act: -0.1700
Data Index: 4101670 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0251. Min Range: -8.0251
Max Act: 6.8688. Min Act: -0.1700
Data Index: 3237316 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19