Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.4562. Min Act: -0.1700
Data Index: 3363948 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.3000. Min Act: -0.1700
Data Index: 4183947 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.2062. Min Act: -0.1700
Data Index: 4188311 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.1125. Min Act: -0.1700
Data Index: 3363945 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.1125. Min Act: -0.1700
Data Index: 3981680 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.1125. Min Act: -0.1700
Data Index: 6543947 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.0812. Min Act: -0.1700
Data Index: 7896765 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4562. Min Range: -7.4562
Max Act: 7.0500. Min Act: -0.1700
Data Index: 3363942 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.9562. Min Act: -0.1700
Data Index: 8332397 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.9250. Min Act: -0.1700
Data Index: 6514322 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8625. Min Act: -0.1700
Data Index: 4415358 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8937. Min Act: -0.1700
Data Index: 1569046 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8312. Min Act: -0.1700
Data Index: 1905531 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8312. Min Act: -0.1700
Data Index: 5808880 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8625. Min Act: -0.1700
Data Index: 7147336 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8312. Min Act: -0.1700
Data Index: 7677596 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8312. Min Act: -0.1700
Data Index: 1796379 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8000. Min Act: -0.1700
Data Index: 5986899 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.8000. Min Act: -0.1700
Data Index: 6276935 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4562. Min Range: -7.4562
Max Act: 6.7687. Min Act: -0.1700
Data Index: 5770548 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19