Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2184 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3850. Min Range: -6.3850
Max Act: 6.3850. Min Act: -0.1700
Data Index: 3532202 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3850. Min Range: -6.3850
Max Act: 6.2288. Min Act: -0.1700
Data Index: 5335448 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3850. Min Range: -6.3850
Max Act: 6.1038. Min Act: -0.1700
Data Index: 7725162 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.7913. Min Act: -0.1700
Data Index: 463525 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.6663. Min Act: -0.1700
Data Index: 8744290 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.6663. Min Act: -0.1700
Data Index: 2629430 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.6038. Min Act: -0.1700
Data Index: 8715691 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5725. Min Act: -0.1700
Data Index: 8829359 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5725. Min Act: -0.1700
Data Index: 6275637 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5725. Min Act: -0.1700
Data Index: 720294 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5413. Min Act: -0.1700
Data Index: 654311 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5100. Min Act: -0.1700
Data Index: 1837105 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5100. Min Act: -0.1700
Data Index: 3376082 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.5100. Min Act: -0.1700
Data Index: 5394631 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.4788. Min Act: -0.1700
Data Index: 1678224 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.4788. Min Act: -0.1700
Data Index: 7223844 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.4788. Min Act: -0.1700
Data Index: 7625396 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.4475. Min Act: -0.1700
Data Index: 5223568 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.4163. Min Act: -0.1700
Data Index: 2376412 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3850. Min Range: -6.3850
Max Act: 5.4163. Min Act: -0.1700
Data Index: 5192666 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19