Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2414 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1726. Min Range: -6.1726
Max Act: 6.1726. Min Act: -0.1700
Data Index: 4800594 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1726. Min Range: -6.1726
Max Act: 6.0789. Min Act: -0.1700
Data Index: 5346404 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1726. Min Range: -6.1726
Max Act: 6.0476. Min Act: -0.1700
Data Index: 1729959 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1726. Min Range: -6.1726
Max Act: 6.0476. Min Act: -0.1700
Data Index: 6141387 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.9851. Min Act: -0.1700
Data Index: 3868414 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.9851. Min Act: -0.1700
Data Index: 8300462 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.8914. Min Act: -0.1700
Data Index: 8531338 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.8601. Min Act: -0.1700
Data Index: 3244886 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.8601. Min Act: -0.1700
Data Index: 1729960 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.8601. Min Act: -0.1700
Data Index: 8818419 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.8914. Min Act: -0.1700
Data Index: 4404262 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2802345 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7976. Min Act: -0.1700
Data Index: 4404263 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7976. Min Act: -0.1700
Data Index: 7859643 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7976. Min Act: -0.1700
Data Index: 6135743 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7976. Min Act: -0.1700
Data Index: 8095886 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7664. Min Act: -0.1700
Data Index: 6202513 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7664. Min Act: -0.1700
Data Index: 4231957 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7664. Min Act: -0.1700
Data Index: 6503545 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1726. Min Range: -6.1726
Max Act: 5.7664. Min Act: -0.1700
Data Index: 6046531 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19