Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.8833. Min Act: -0.1700
Data Index: 5107564 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.8521. Min Act: -0.1700
Data Index: 5203570 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.7583. Min Act: -0.1700
Data Index: 3933630 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.7583. Min Act: -0.1700
Data Index: 6991275 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.4458. Min Act: -0.1700
Data Index: 8414383 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.4458. Min Act: -0.1700
Data Index: 2027330 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.4458. Min Act: -0.1700
Data Index: 1072664 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.4146. Min Act: -0.1700
Data Index: 5051214 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.4146. Min Act: -0.1700
Data Index: 8185119 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.3521. Min Act: -0.1700
Data Index: 4523883 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.3521. Min Act: -0.1700
Data Index: 1975046 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.3521. Min Act: -0.1700
Data Index: 1803736 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.3208. Min Act: -0.1700
Data Index: 2076816 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.3208. Min Act: -0.1700
Data Index: 165147 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.2896. Min Act: -0.1700
Data Index: 7677058 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.2896. Min Act: -0.1700
Data Index: 6134705 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.2896. Min Act: -0.1700
Data Index: 6301957 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.2896. Min Act: -0.1700
Data Index: 5939188 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.2896. Min Act: -0.1700
Data Index: 4823833 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8833. Min Range: -6.8833
Max Act: 6.2896. Min Act: -0.1700
Data Index: 497010 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19