Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3933. Min Range: -7.3933
Max Act: 7.3933. Min Act: -0.1700
Data Index: 901615 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3933. Min Range: -7.3933
Max Act: 7.3621. Min Act: -0.1700
Data Index: 7454841 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3933. Min Range: -7.3933
Max Act: 7.2058. Min Act: -0.1700
Data Index: 737539 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3933. Min Range: -7.3933
Max Act: 7.1433. Min Act: -0.1700
Data Index: 7053027 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3933. Min Range: -7.3933
Max Act: 7.0183. Min Act: -0.1700
Data Index: 7033438 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.9558. Min Act: -0.1700
Data Index: 3187553 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8933. Min Act: -0.1700
Data Index: 5552794 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8621. Min Act: -0.1700
Data Index: 5218112 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8933. Min Act: -0.1700
Data Index: 2202410 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8933. Min Act: -0.1700
Data Index: 8647662 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8621. Min Act: -0.1700
Data Index: 1599379 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8621. Min Act: -0.1700
Data Index: 4263012 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.8308. Min Act: -0.1700
Data Index: 4839848 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.7058. Min Act: -0.1700
Data Index: 2939945 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.7371. Min Act: -0.1700
Data Index: 5127838 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.7058. Min Act: -0.1700
Data Index: 5520359 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.7058. Min Act: -0.1700
Data Index: 3550582 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.6746. Min Act: -0.1700
Data Index: 2163616 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.6746. Min Act: -0.1700
Data Index: 3668832 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3933. Min Range: -7.3933
Max Act: 6.6433. Min Act: -0.1700
Data Index: 3350792 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19