Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.1512. Min Act: -0.1700
Data Index: 1843712 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.1512. Min Act: -0.1700
Data Index: 1942166 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.1200. Min Act: -0.1700
Data Index: 113619 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 4834104 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0575. Min Act: -0.1700
Data Index: 1190412 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 2694745 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0575. Min Act: -0.1700
Data Index: 3366818 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 7338148 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0575. Min Act: -0.1700
Data Index: 6559747 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0575. Min Act: -0.1700
Data Index: 1630146 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0262. Min Act: -0.1700
Data Index: 460632 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0575. Min Act: -0.1700
Data Index: 6873194 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0262. Min Act: -0.1700
Data Index: 7716898 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0575. Min Act: -0.1700
Data Index: 5011146 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1512. Min Range: -6.1512
Max Act: 5.9950. Min Act: -0.1700
Data Index: 6185854 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1512. Min Range: -6.1512
Max Act: 5.9950. Min Act: -0.1700
Data Index: 2514158 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1512. Min Range: -6.1512
Max Act: 5.9950. Min Act: -0.1700
Data Index: 6016880 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1512. Min Range: -6.1512
Max Act: 6.0262. Min Act: -0.1700
Data Index: 978404 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1512. Min Range: -6.1512
Max Act: 5.9950. Min Act: -0.1700
Data Index: 653301 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1512. Min Range: -6.1512
Max Act: 5.9637. Min Act: -0.1700
Data Index: 4020114 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19