Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0452. Min Range: -7.0452
Max Act: 7.0452. Min Act: -0.1700
Data Index: 4714145 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.8889. Min Act: -0.1700
Data Index: 1500607 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.8889. Min Act: -0.1700
Data Index: 6339342 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.7952. Min Act: -0.1700
Data Index: 398457 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.7952. Min Act: -0.1700
Data Index: 2144721 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.7014. Min Act: -0.1700
Data Index: 4072505 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.7014. Min Act: -0.1700
Data Index: 3388649 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6389. Min Act: -0.1700
Data Index: 5737855 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6389. Min Act: -0.1700
Data Index: 7071497 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6389. Min Act: -0.1700
Data Index: 3577551 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6077. Min Act: -0.1700
Data Index: 3161706 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6077. Min Act: -0.1700
Data Index: 4138266 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6389. Min Act: -0.1700
Data Index: 2567703 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.6077. Min Act: -0.1700
Data Index: 4138265 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.5764. Min Act: -0.1700
Data Index: 1271251 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.5764. Min Act: -0.1700
Data Index: 3113843 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.5452. Min Act: -0.1700
Data Index: 53545 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.5452. Min Act: -0.1700
Data Index: 311566 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.5139. Min Act: -0.1700
Data Index: 211550 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0452. Min Range: -7.0452
Max Act: 6.5139. Min Act: -0.1700
Data Index: 1022840 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19