Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.2596. Min Act: -0.1700
Data Index: 3967456 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.1346. Min Act: -0.1700
Data Index: 7248473 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.1033. Min Act: -0.1700
Data Index: 7713674 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0721. Min Act: -0.1700
Data Index: 7495706 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0408. Min Act: -0.1700
Data Index: 1206590 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0096. Min Act: -0.1700
Data Index: 8068942 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0408. Min Act: -0.1700
Data Index: 8532368 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 6189863 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 4500448 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0096. Min Act: -0.1700
Data Index: 1849916 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0096. Min Act: -0.1700
Data Index: 8431050 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0096. Min Act: -0.1700
Data Index: 326483 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2596. Min Range: -5.2596
Max Act: 5.0096. Min Act: -0.1700
Data Index: 7322053 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3615540 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 8068928 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 332769 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3947762 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 4367496 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 2615939 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2596. Min Range: -5.2596
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3137710 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19