Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1466. Min Range: -8.1466
Max Act: 8.1466. Min Act: -0.1700
Data Index: 5615620 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1466. Min Range: -8.1466
Max Act: 8.1466. Min Act: -0.1700
Data Index: 8825584 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1466. Min Range: -8.1466
Max Act: 8.0841. Min Act: -0.1700
Data Index: 5940823 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1466. Min Range: -8.1466
Max Act: 8.0216. Min Act: -0.1700
Data Index: 5442861 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1466. Min Range: -8.1466
Max Act: 8.0216. Min Act: -0.1700
Data Index: 4700717 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.9591. Min Act: -0.1700
Data Index: 4690288 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.9591. Min Act: -0.1700
Data Index: 5264138 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 4470952 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 5065655 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 5570646 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 5238820 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.8966. Min Act: -0.1700
Data Index: 3321437 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.8341. Min Act: -0.1700
Data Index: 4357856 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7716. Min Act: -0.1700
Data Index: 8562291 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7716. Min Act: -0.1700
Data Index: 5568205 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7716. Min Act: -0.1700
Data Index: 3484300 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7716. Min Act: -0.1700
Data Index: 7904491 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7091. Min Act: -0.1700
Data Index: 5238819 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7091. Min Act: -0.1700
Data Index: 5262937 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1466. Min Range: -8.1466
Max Act: 7.7091. Min Act: -0.1700
Data Index: 2882382 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19