Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.8841. Min Act: -0.1700
Data Index: 5240397 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.8046. Min Act: -0.1700
Data Index: 2477019 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7887. Min Act: -0.1700
Data Index: 3839809 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7728. Min Act: -0.1700
Data Index: 4448716 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7728. Min Act: -0.1700
Data Index: 7220659 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7568. Min Act: -0.1700
Data Index: 807647 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7568. Min Act: -0.1700
Data Index: 1774314 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7249. Min Act: -0.1700
Data Index: 3124955 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7249. Min Act: -0.1700
Data Index: 3265399 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7089. Min Act: -0.1700
Data Index: 5415968 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.7089. Min Act: -0.1700
Data Index: 4440262 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6929. Min Act: -0.1700
Data Index: 3957781 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6929. Min Act: -0.1700
Data Index: 6760526 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6929. Min Act: -0.1700
Data Index: 5969744 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6929. Min Act: -0.1700
Data Index: 6035029 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6929. Min Act: -0.1700
Data Index: 6167169 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6929. Min Act: -0.1700
Data Index: 210881 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6769. Min Act: -0.1700
Data Index: 3183150 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6769. Min Act: -0.1700
Data Index: 5458749 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8841. Min Range: -2.8841
Max Act: 2.6608. Min Act: -0.1700
Data Index: 1903033 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19