Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2183 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1535. Min Range: -5.1535
Max Act: 5.1535. Min Act: -0.1700
Data Index: 2619593 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1535. Min Range: -5.1535
Max Act: 5.0910. Min Act: -0.1700
Data Index: 1475223 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1535. Min Range: -5.1535
Max Act: 5.0910. Min Act: -0.1700
Data Index: 132042 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1535. Min Range: -5.1535
Max Act: 5.0597. Min Act: -0.1700
Data Index: 6975019 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1535. Min Range: -5.1535
Max Act: 5.0285. Min Act: -0.1700
Data Index: 6607678 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9972. Min Act: -0.1700
Data Index: 3433581 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1535. Min Range: -5.1535
Max Act: 5.0285. Min Act: -0.1700
Data Index: 1607647 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9972. Min Act: -0.1700
Data Index: 7462464 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9972. Min Act: -0.1700
Data Index: 238685 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9347. Min Act: -0.1700
Data Index: 108796 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9035. Min Act: -0.1700
Data Index: 2563591 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9347. Min Act: -0.1700
Data Index: 8400610 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9035. Min Act: -0.1700
Data Index: 2352393 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9035. Min Act: -0.1700
Data Index: 314368 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.9035. Min Act: -0.1700
Data Index: 8547875 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.8722. Min Act: -0.1700
Data Index: 5677183 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.8722. Min Act: -0.1700
Data Index: 4311314 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.8097. Min Act: -0.1700
Data Index: 5694906 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.8097. Min Act: -0.1700
Data Index: 7130929 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1535. Min Range: -5.1535
Max Act: 4.8097. Min Act: -0.1700
Data Index: 4404066 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19