Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4757 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1535. Min Range: -6.1535
Max Act: 6.1535. Min Act: -0.1700
Data Index: 4963112 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1535. Min Range: -6.1535
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2131480 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.9972. Min Act: -0.1700
Data Index: 7647096 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.9660. Min Act: -0.1700
Data Index: 2309012 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.9035. Min Act: -0.1700
Data Index: 708888 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 4191702 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8722. Min Act: -0.1700
Data Index: 4831597 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.9035. Min Act: -0.1700
Data Index: 2292167 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8722. Min Act: -0.1700
Data Index: 8672890 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 7072255 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 4582781 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8722. Min Act: -0.1700
Data Index: 7549896 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8410. Min Act: -0.1700
Data Index: 4891396 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 3030423 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 4266970 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6919309 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 7159477 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6873681 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6517881 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1535. Min Range: -6.1535
Max Act: 5.8097. Min Act: -0.1700
Data Index: 551155 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19