Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.5720. Min Act: -0.1700
Data Index: 2089153 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.5095. Min Act: -0.1700
Data Index: 5551846 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.3533. Min Act: -0.1700
Data Index: 7326217 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.3220. Min Act: -0.1700
Data Index: 777191 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.2908. Min Act: -0.1700
Data Index: 2245000 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.2283. Min Act: -0.1700
Data Index: 1249898 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4101348 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.2283. Min Act: -0.1700
Data Index: 7727721 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1970. Min Act: -0.1700
Data Index: 944222 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1970. Min Act: -0.1700
Data Index: 1981779 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1970. Min Act: -0.1700
Data Index: 1864817 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1970. Min Act: -0.1700
Data Index: 4953550 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1658. Min Act: -0.1700
Data Index: 5449385 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1658. Min Act: -0.1700
Data Index: 493579 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1658. Min Act: -0.1700
Data Index: 2467879 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1658. Min Act: -0.1700
Data Index: 5384865 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1345. Min Act: -0.1700
Data Index: 339267 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1345. Min Act: -0.1700
Data Index: 5433699 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.1345. Min Act: -0.1700
Data Index: 6400632 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5720. Min Range: -5.5720
Max Act: 5.0720. Min Act: -0.1700
Data Index: 513959 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19