Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3088. Min Range: -9.3088
Max Act: 9.3088. Min Act: -0.1700
Data Index: 6334602 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3088. Min Range: -9.3088
Max Act: 9.1213. Min Act: -0.1700
Data Index: 1813389 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3088. Min Range: -9.3088
Max Act: 9.0588. Min Act: -0.1700
Data Index: 6840570 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.9338. Min Act: -0.1700
Data Index: 8769788 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8713. Min Act: -0.1700
Data Index: 1687669 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.9338. Min Act: -0.1700
Data Index: 7489245 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.9338. Min Act: -0.1700
Data Index: 6651605 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8088. Min Act: -0.1700
Data Index: 1171300 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8088. Min Act: -0.1700
Data Index: 5086946 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8088. Min Act: -0.1700
Data Index: 4018082 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8088. Min Act: -0.1700
Data Index: 1972652 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8088. Min Act: -0.1700
Data Index: 2131138 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.8088. Min Act: -0.1700
Data Index: 1969157 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.7463. Min Act: -0.1700
Data Index: 6716206 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.7463. Min Act: -0.1700
Data Index: 3411885 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.7463. Min Act: -0.1700
Data Index: 7830290 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.7463. Min Act: -0.1700
Data Index: 7071256 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.6838. Min Act: -0.1700
Data Index: 4788125 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.6838. Min Act: -0.1700
Data Index: 4157795 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3088. Min Range: -9.3088
Max Act: 8.6838. Min Act: -0.1700
Data Index: 7155446 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19