Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 261 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.9728. Min Act: -0.1700
Data Index: 4962744 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0040. Min Range: -6.0040
Max Act: 6.0040. Min Act: -0.1700
Data Index: 5301002 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.8790. Min Act: -0.1700
Data Index: 893241 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.7853. Min Act: -0.1700
Data Index: 7975397 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.7540. Min Act: -0.1700
Data Index: 6866376 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.7853. Min Act: -0.1700
Data Index: 4446948 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.7540. Min Act: -0.1700
Data Index: 2496100 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.7228. Min Act: -0.1700
Data Index: 3151118 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6915. Min Act: -0.1700
Data Index: 4092555 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6915. Min Act: -0.1700
Data Index: 4583716 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6915. Min Act: -0.1700
Data Index: 2047604 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6603. Min Act: -0.1700
Data Index: 138927 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6603. Min Act: -0.1700
Data Index: 8815421 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6290. Min Act: -0.1700
Data Index: 6395383 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.6290. Min Act: -0.1700
Data Index: 3904217 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.5978. Min Act: -0.1700
Data Index: 2124176 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.5978. Min Act: -0.1700
Data Index: 4774946 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.5978. Min Act: -0.1700
Data Index: 1393263 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.5978. Min Act: -0.1700
Data Index: 6969917 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0040. Min Range: -6.0040
Max Act: 5.5665. Min Act: -0.1700
Data Index: 4808521 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19