Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.8157. Min Act: -0.1700
Data Index: 7912914 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.7219. Min Act: -0.1700
Data Index: 8179084 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.6282. Min Act: -0.1700
Data Index: 4458018 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.5657. Min Act: -0.1700
Data Index: 7895802 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.5657. Min Act: -0.1700
Data Index: 3032156 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.5344. Min Act: -0.1700
Data Index: 1949846 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.5344. Min Act: -0.1700
Data Index: 3573046 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.5032. Min Act: -0.1700
Data Index: 8525055 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.5032. Min Act: -0.1700
Data Index: 625060 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.4719. Min Act: -0.1700
Data Index: 5066340 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.4094. Min Act: -0.1700
Data Index: 2154565 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3782. Min Act: -0.1700
Data Index: 4890501 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3782. Min Act: -0.1700
Data Index: 7656353 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3782. Min Act: -0.1700
Data Index: 7869724 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3469. Min Act: -0.1700
Data Index: 5789849 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2084281 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3157. Min Act: -0.1700
Data Index: 4615060 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.3157. Min Act: -0.1700
Data Index: 8756362 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.2844. Min Act: -0.1700
Data Index: 5571776 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8157. Min Range: -6.8157
Max Act: 6.2844. Min Act: -0.1700
Data Index: 5596673 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19