Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 383 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0777. Min Range: -8.0777
Max Act: 8.0777. Min Act: -0.1700
Data Index: 1773230 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.8902. Min Act: -0.1700
Data Index: 5569361 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.6090. Min Act: -0.1700
Data Index: 4587138 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.5777. Min Act: -0.1700
Data Index: 4617172 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.6090. Min Act: -0.1700
Data Index: 1865585 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.4840. Min Act: -0.1700
Data Index: 1280673 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.3902. Min Act: -0.1700
Data Index: 3851669 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.3902. Min Act: -0.1700
Data Index: 3691450 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.3590. Min Act: -0.1700
Data Index: 1459598 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.3277. Min Act: -0.1700
Data Index: 2137073 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.3590. Min Act: -0.1700
Data Index: 5413677 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.3277. Min Act: -0.1700
Data Index: 2899253 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2965. Min Act: -0.1700
Data Index: 2011840 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2965. Min Act: -0.1700
Data Index: 7636633 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2965. Min Act: -0.1700
Data Index: 5532517 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 8517540 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 4600977 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2027. Min Act: -0.1700
Data Index: 1364643 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2027. Min Act: -0.1700
Data Index: 6397337 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0777. Min Range: -8.0777
Max Act: 7.2340. Min Act: -0.1700
Data Index: 2319923 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19