Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.5182. Min Act: -0.1700
Data Index: 350951 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.2057. Min Act: -0.1700
Data Index: 3145411 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1744. Min Act: -0.1700
Data Index: 2610886 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1432. Min Act: -0.1700
Data Index: 6859974 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1432. Min Act: -0.1700
Data Index: 5015464 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1432. Min Act: -0.1700
Data Index: 3070326 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1119. Min Act: -0.1700
Data Index: 2383726 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1119. Min Act: -0.1700
Data Index: 8767603 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.1119. Min Act: -0.1700
Data Index: 3686767 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0807. Min Act: -0.1700
Data Index: 7188347 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0807. Min Act: -0.1700
Data Index: 1386301 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0494. Min Act: -0.1700
Data Index: 8462019 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0494. Min Act: -0.1700
Data Index: 6843403 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0494. Min Act: -0.1700
Data Index: 8291659 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0182. Min Act: -0.1700
Data Index: 4342056 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0182. Min Act: -0.1700
Data Index: 732113 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5182. Min Range: -6.5182
Max Act: 5.9869. Min Act: -0.1700
Data Index: 235060 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0182. Min Act: -0.1700
Data Index: 5684133 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5182. Min Range: -6.5182
Max Act: 6.0182. Min Act: -0.1700
Data Index: 6878138 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5182. Min Range: -6.5182
Max Act: 5.9869. Min Act: -0.1700
Data Index: 6763079 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19