Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9674. Min Act: -0.1700
Data Index: 2584464 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9049. Min Act: -0.1700
Data Index: 2987157 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9049. Min Act: -0.1700
Data Index: 1653038 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8736. Min Act: -0.1700
Data Index: 200947 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 1501591 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 1278628 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 5806033 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 7183707 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 5228105 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8111. Min Act: -0.1700
Data Index: 1835037 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8111. Min Act: -0.1700
Data Index: 5942517 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8111. Min Act: -0.1700
Data Index: 6088677 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 6373667 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 1994501 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 5693935 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 3239965 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 2987158 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 5901819 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 3882478 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7486. Min Act: -0.1700
Data Index: 1223040 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19