Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.8778. Min Act: -0.1700
Data Index: 5648003 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8722364 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.7528. Min Act: -0.1700
Data Index: 4587761 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.7528. Min Act: -0.1700
Data Index: 8572680 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.7215. Min Act: -0.1700
Data Index: 3144347 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.7215. Min Act: -0.1700
Data Index: 8741442 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.6903. Min Act: -0.1700
Data Index: 7765842 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.6590. Min Act: -0.1700
Data Index: 2494796 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5965. Min Act: -0.1700
Data Index: 4877237 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5653. Min Act: -0.1700
Data Index: 17294 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5653. Min Act: -0.1700
Data Index: 7936821 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5653. Min Act: -0.1700
Data Index: 243149 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5653. Min Act: -0.1700
Data Index: 1814818 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5028. Min Act: -0.1700
Data Index: 6493626 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5028. Min Act: -0.1700
Data Index: 859220 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7617232 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5028. Min Act: -0.1700
Data Index: 7584265 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5028. Min Act: -0.1700
Data Index: 5438925 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.5028. Min Act: -0.1700
Data Index: 2523918 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8778. Min Range: -5.8778
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6143647 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19