Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0953. Min Range: -7.0953
Max Act: 7.0953. Min Act: -0.1700
Data Index: 2824855 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0953. Min Range: -7.0953
Max Act: 7.0640. Min Act: -0.1700
Data Index: 8740130 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.9390. Min Act: -0.1700
Data Index: 5521570 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.9078. Min Act: -0.1700
Data Index: 6623258 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.8765. Min Act: -0.1700
Data Index: 4815586 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.8453. Min Act: -0.1700
Data Index: 1922872 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.8140. Min Act: -0.1700
Data Index: 663920 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.8140. Min Act: -0.1700
Data Index: 2364742 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7515. Min Act: -0.1700
Data Index: 4826822 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7828. Min Act: -0.1700
Data Index: 4170270 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7515. Min Act: -0.1700
Data Index: 3233194 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7515. Min Act: -0.1700
Data Index: 3760091 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7895708 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6890. Min Act: -0.1700
Data Index: 7040894 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 4909275 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 5373445 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 3070331 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 2438023 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 2222573 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 3940719 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19