Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.6910. Min Act: -0.1700
Data Index: 4489686 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.6910. Min Act: -0.1700
Data Index: 1832538 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.6598. Min Act: -0.1700
Data Index: 4827872 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5973. Min Act: -0.1700
Data Index: 8650818 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.6285. Min Act: -0.1700
Data Index: 1936976 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5973. Min Act: -0.1700
Data Index: 2611089 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5660. Min Act: -0.1700
Data Index: 3563500 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5973. Min Act: -0.1700
Data Index: 7118693 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5660. Min Act: -0.1700
Data Index: 6841145 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5660. Min Act: -0.1700
Data Index: 131434 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5973. Min Act: -0.1700
Data Index: 1364085 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5660. Min Act: -0.1700
Data Index: 5333815 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5660. Min Act: -0.1700
Data Index: 1142453 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5348. Min Act: -0.1700
Data Index: 1851053 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5348. Min Act: -0.1700
Data Index: 7357455 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5348. Min Act: -0.1700
Data Index: 2131440 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5035. Min Act: -0.1700
Data Index: 6067491 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5035. Min Act: -0.1700
Data Index: 2132102 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.5035. Min Act: -0.1700
Data Index: 2656915 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6910. Min Range: -5.6910
Max Act: 5.4723. Min Act: -0.1700
Data Index: 7604393 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19