Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8888. Min Act: -0.1700
Data Index: 479064 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8633. Min Act: -0.1700
Data Index: 2881915 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8633. Min Act: -0.1592
Data Index: 1465827 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8463. Min Act: -0.1700
Data Index: 5848539 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8463. Min Act: -0.1689
Data Index: 5422237 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8294. Min Act: -0.1700
Data Index: 3976115 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8379. Min Act: -0.1687
Data Index: 4040174 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.8379. Min Act: -0.1695
Data Index: 7364104 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7958. Min Act: -0.1674
Data Index: 6108035 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7958. Min Act: -0.1699
Data Index: 511350 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7874. Min Act: -0.1674
Data Index: 1347634 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7874. Min Act: -0.1699
Data Index: 4681585 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7874. Min Act: -0.1688
Data Index: 6596405 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7707. Min Act: -0.1700
Data Index: 7797011 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7707. Min Act: -0.1700
Data Index: 8390828 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7624. Min Act: -0.1700
Data Index: 5945119 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7624. Min Act: -0.1700
Data Index: 6658481 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7624. Min Act: -0.1700
Data Index: 4619075 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7624. Min Act: -0.1700
Data Index: 8480723 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8888. Min Range: -0.8888
Max Act: 0.7624. Min Act: -0.1650
Data Index: 5261556 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19