Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2344 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.8039. Min Act: -0.1700
Data Index: 2950859 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.4601. Min Act: -0.1700
Data Index: 7687897 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.3351. Min Act: -0.1700
Data Index: 7408747 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.3351. Min Act: -0.1700
Data Index: 320503 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.3039. Min Act: -0.1700
Data Index: 5649549 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.2101. Min Act: -0.1700
Data Index: 6317604 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.2101. Min Act: -0.1700
Data Index: 5532267 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.1789. Min Act: -0.1700
Data Index: 4221415 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.1789. Min Act: -0.1700
Data Index: 1022168 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.1789. Min Act: -0.1700
Data Index: 6259291 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.1476. Min Act: -0.1700
Data Index: 7328423 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.1476. Min Act: -0.1700
Data Index: 8794692 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.1164. Min Act: -0.1700
Data Index: 2256369 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.0539. Min Act: -0.1700
Data Index: 338895 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8039. Min Range: -7.8039
Max Act: 7.0539. Min Act: -0.1700
Data Index: 7966306 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8039. Min Range: -7.8039
Max Act: 6.9914. Min Act: -0.1700
Data Index: 6445986 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8039. Min Range: -7.8039
Max Act: 6.9601. Min Act: -0.1700
Data Index: 5128606 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8039. Min Range: -7.8039
Max Act: 6.9914. Min Act: -0.1700
Data Index: 4830546 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8039. Min Range: -7.8039
Max Act: 6.9914. Min Act: -0.1700
Data Index: 1111559 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8039. Min Range: -7.8039
Max Act: 6.9914. Min Act: -0.1700
Data Index: 7285568 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19