Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1868. Min Act: -0.1700
Data Index: 6445246 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1554. Min Act: -0.1700
Data Index: 2576054 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1554. Min Act: -0.1700
Data Index: 8735639 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1396. Min Act: -0.1700
Data Index: 3902373 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1396. Min Act: -0.1700
Data Index: 7528874 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1396. Min Act: -0.1700
Data Index: 2798069 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1239. Min Act: -0.1700
Data Index: 1720267 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1081. Min Act: -0.1700
Data Index: 6377492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1081. Min Act: -0.1700
Data Index: 7781934 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1081. Min Act: -0.1700
Data Index: 8713636 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1239. Min Act: -0.1700
Data Index: 320904 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.1081. Min Act: -0.1700
Data Index: 7903275 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0923. Min Act: -0.1700
Data Index: 3972270 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0923. Min Act: -0.1700
Data Index: 8226234 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0923. Min Act: -0.1700
Data Index: 3715836 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0766. Min Act: -0.1700
Data Index: 1810437 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0766. Min Act: -0.1700
Data Index: 5370698 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0766. Min Act: -0.1700
Data Index: 2505378 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0608. Min Act: -0.1700
Data Index: 4194322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1868. Min Range: -3.1868
Max Act: 3.0608. Min Act: -0.1700
Data Index: 904295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19