Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0581. Min Range: -6.0581
Max Act: 6.0581. Min Act: -0.1700
Data Index: 5442696 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.8706. Min Act: -0.1700
Data Index: 2132486 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.8394. Min Act: -0.1700
Data Index: 8799861 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.8394. Min Act: -0.1700
Data Index: 2493489 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.8394. Min Act: -0.1700
Data Index: 7817055 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.8394. Min Act: -0.1700
Data Index: 560476 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7769. Min Act: -0.1700
Data Index: 7812094 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7769. Min Act: -0.1700
Data Index: 160686 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7456. Min Act: -0.1700
Data Index: 5143799 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 5924875 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7769. Min Act: -0.1700
Data Index: 4781174 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7456. Min Act: -0.1700
Data Index: 4602714 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7456. Min Act: -0.1700
Data Index: 8528634 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 5745007 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7456. Min Act: -0.1700
Data Index: 7288913 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 1579624 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 7873691 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 6887585 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 7926202 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0581. Min Range: -6.0581
Max Act: 5.7144. Min Act: -0.1700
Data Index: 8435882 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19