Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3810. Min Act: -0.1700
Data Index: 6475075 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3496. Min Act: -0.1700
Data Index: 5556785 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3339. Min Act: -0.1700
Data Index: 2830745 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3339. Min Act: -0.1700
Data Index: 8401734 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3339. Min Act: -0.1700
Data Index: 3019876 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3182. Min Act: -0.1700
Data Index: 8476917 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3182. Min Act: -0.1700
Data Index: 7302663 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.3182. Min Act: -0.1700
Data Index: 3770483 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2554. Min Act: -0.1700
Data Index: 7327241 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2869. Min Act: -0.1700
Data Index: 1665037 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2554. Min Act: -0.1700
Data Index: 5868385 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2397. Min Act: -0.1700
Data Index: 4447473 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2240. Min Act: -0.1700
Data Index: 4224534 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2240. Min Act: -0.1700
Data Index: 3715311 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2240. Min Act: -0.1700
Data Index: 1918043 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2240. Min Act: -0.1700
Data Index: 3885866 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.1926. Min Act: -0.1700
Data Index: 160910 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.1926. Min Act: -0.1700
Data Index: 2890798 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.1926. Min Act: -0.1700
Data Index: 4337547 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3810. Min Range: -3.3810
Max Act: 3.2083. Min Act: -0.1700
Data Index: 7205582 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19