Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.8012. Min Act: -0.1700
Data Index: 6637094 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.7387. Min Act: -0.1700
Data Index: 1107259 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.6137. Min Act: -0.1700
Data Index: 3950484 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.5512. Min Act: -0.1700
Data Index: 8766357 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.4887. Min Act: -0.1700
Data Index: 6474271 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.4887. Min Act: -0.1700
Data Index: 8470080 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.4262. Min Act: -0.1700
Data Index: 6590166 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.4887. Min Act: -0.1700
Data Index: 4825744 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.4262. Min Act: -0.1700
Data Index: 6860670 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.4262. Min Act: -0.1700
Data Index: 1163677 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.3637. Min Act: -0.1700
Data Index: 4754772 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.3012. Min Act: -0.1700
Data Index: 683609 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.3012. Min Act: -0.1700
Data Index: 5165193 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.2387. Min Act: -0.1700
Data Index: 4242211 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.2387. Min Act: -0.1700
Data Index: 8268723 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.2387. Min Act: -0.1700
Data Index: 6590165 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.1762. Min Act: -0.1700
Data Index: 3276314 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.1762. Min Act: -0.1700
Data Index: 3161012 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.1762. Min Act: -0.1700
Data Index: 6342957 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8012. Min Range: -8.8012
Max Act: 8.1137. Min Act: -0.1700
Data Index: 6164718 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19