Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5251 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2203. Min Range: -10.2203
Max Act: 10.2203. Min Act: -0.1700
Data Index: 8425880 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2203. Min Range: -10.2203
Max Act: 10.2203. Min Act: -0.1700
Data Index: 5744724 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2203. Min Range: -10.2203
Max Act: 10.0953. Min Act: -0.1700
Data Index: 3505202 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2203. Min Range: -10.2203
Max Act: 10.0953. Min Act: -0.1700
Data Index: 227643 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.9703. Min Act: -0.1700
Data Index: 158752 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.9703. Min Act: -0.1700
Data Index: 3390088 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.9703. Min Act: -0.1700
Data Index: 17921 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.9703. Min Act: -0.1700
Data Index: 6937582 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.9703. Min Act: -0.1700
Data Index: 1098799 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.9078. Min Act: -0.1699
Data Index: 4713938 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.8453. Min Act: -0.1700
Data Index: 4865046 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.8453. Min Act: -0.1700
Data Index: 8398816 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.8453. Min Act: -0.1700
Data Index: 4029896 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7828. Min Act: -0.1700
Data Index: 7558902 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7828. Min Act: -0.1700
Data Index: 678064 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7203. Min Act: -0.1700
Data Index: 6347066 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7203. Min Act: -0.1700
Data Index: 123738 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7203. Min Act: -0.1700
Data Index: 2100025 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7828. Min Act: -0.1700
Data Index: 4267721 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2203. Min Range: -10.2203
Max Act: 9.7203. Min Act: -0.1700
Data Index: 7299324 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19