Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.9947. Min Act: -0.1700
Data Index: 8525755 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.7447. Min Act: -0.1700
Data Index: 8525756 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.3697. Min Act: -0.1700
Data Index: 3293950 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.3072. Min Act: -0.1700
Data Index: 2599908 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.2447. Min Act: -0.1700
Data Index: 1667638 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.0572. Min Act: -0.1700
Data Index: 3943569 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.9947. Min Act: -0.1700
Data Index: 1557379 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9947. Min Range: -8.9947
Max Act: 8.0572. Min Act: -0.1700
Data Index: 363638 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.9947. Min Act: -0.1700
Data Index: 3193217 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.9947. Min Act: -0.1700
Data Index: 5133598 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.9635. Min Act: -0.1700
Data Index: 1693224 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.9635. Min Act: -0.1700
Data Index: 8336334 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.8385. Min Act: -0.1700
Data Index: 7837571 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.7447. Min Act: -0.1700
Data Index: 3858861 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.7135. Min Act: -0.1700
Data Index: 853964 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.7135. Min Act: -0.1700
Data Index: 3943568 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.6510. Min Act: -0.1700
Data Index: 5633602 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.5885. Min Act: -0.1700
Data Index: 3475382 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.5572. Min Act: -0.1700
Data Index: 8826927 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9947. Min Range: -8.9947
Max Act: 7.5572. Min Act: -0.1700
Data Index: 350616 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19