Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.7551. Min Act: -0.1700
Data Index: 4493517 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.7238. Min Act: -0.1700
Data Index: 4860172 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.6613. Min Act: -0.1700
Data Index: 4228425 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.6613. Min Act: -0.1700
Data Index: 4860176 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.5988. Min Act: -0.1700
Data Index: 218315 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.5363. Min Act: -0.1700
Data Index: 2889943 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.5363. Min Act: -0.1700
Data Index: 6657391 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.5051. Min Act: -0.1700
Data Index: 1654406 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.5363. Min Act: -0.1700
Data Index: 750684 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.4738. Min Act: -0.1700
Data Index: 645440 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.4426. Min Act: -0.1700
Data Index: 4072232 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.3801. Min Act: -0.1700
Data Index: 586796 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.3488. Min Act: -0.1700
Data Index: 4075011 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.2863. Min Act: -0.1700
Data Index: 117928 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.2863. Min Act: -0.1700
Data Index: 6607736 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.2863. Min Act: -0.1700
Data Index: 2593864 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.2551. Min Act: -0.1700
Data Index: 2902623 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.1926. Min Act: -0.1700
Data Index: 3764876 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.1926. Min Act: -0.1700
Data Index: 6917046 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7551. Min Range: -6.7551
Max Act: 6.1926. Min Act: -0.1700
Data Index: 2524069 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19