Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2543 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.9818. Min Act: -0.1700
Data Index: 502155 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.9193. Min Act: -0.1700
Data Index: 5562061 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.7943. Min Act: -0.1700
Data Index: 3421661 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.7006. Min Act: -0.1700
Data Index: 2590492 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.6693. Min Act: -0.1700
Data Index: 8749456 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.6693. Min Act: -0.1700
Data Index: 4901592 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.6381. Min Act: -0.1700
Data Index: 8318908 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5756. Min Act: -0.1700
Data Index: 2421431 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5756. Min Act: -0.1700
Data Index: 1675758 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5756. Min Act: -0.1700
Data Index: 1607667 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5443. Min Act: -0.1700
Data Index: 946406 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5443. Min Act: -0.1700
Data Index: 359882 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5443. Min Act: -0.1700
Data Index: 3207147 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5443. Min Act: -0.1700
Data Index: 138480 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.5131. Min Act: -0.1700
Data Index: 2017448 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.4818. Min Act: -0.1700
Data Index: 8401352 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.4506. Min Act: -0.1700
Data Index: 6022057 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.4506. Min Act: -0.1700
Data Index: 2383070 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.4506. Min Act: -0.1700
Data Index: 3421660 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9818. Min Range: -5.9818
Max Act: 5.4506. Min Act: -0.1700
Data Index: 507317 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19