Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4406 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0001. Min Range: -6.0001
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6269277 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0001. Min Range: -6.0001
Max Act: 6.0001. Min Act: -0.1700
Data Index: 1045491 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.9064. Min Act: -0.1700
Data Index: 1012789 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.9064. Min Act: -0.1700
Data Index: 317841 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.9064. Min Act: -0.1700
Data Index: 5521421 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 5945769 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 6759744 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 3994649 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 4461777 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 7138877 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 8552844 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8751. Min Act: -0.1700
Data Index: 4577787 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.9064. Min Act: -0.1700
Data Index: 3444222 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8439. Min Act: -0.1700
Data Index: 6248366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8439. Min Act: -0.1700
Data Index: 5812072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8439. Min Act: -0.1700
Data Index: 5701331 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8439. Min Act: -0.1700
Data Index: 2915193 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8439. Min Act: -0.1700
Data Index: 8366320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8439. Min Act: -0.1700
Data Index: 3007049 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0001. Min Range: -6.0001
Max Act: 5.8126. Min Act: -0.1700
Data Index: 7462088 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19