Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.9788. Min Act: -0.1700
Data Index: 1861057 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.9475. Min Act: -0.1700
Data Index: 1669210 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.8225. Min Act: -0.1700
Data Index: 336840 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.8225. Min Act: -0.1700
Data Index: 1923661 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.7600. Min Act: -0.1700
Data Index: 3798594 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.7288. Min Act: -0.1700
Data Index: 4271867 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.6975. Min Act: -0.1700
Data Index: 161680 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.6975. Min Act: -0.1700
Data Index: 1294261 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.6663. Min Act: -0.1700
Data Index: 6443036 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.6975. Min Act: -0.1700
Data Index: 3737630 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.6038. Min Act: -0.1700
Data Index: 6844485 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.5725. Min Act: -0.1700
Data Index: 8083763 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.4788. Min Act: -0.1700
Data Index: 2513879 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.4475. Min Act: -0.1700
Data Index: 7702997 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.4163. Min Act: -0.1700
Data Index: 591364 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.4163. Min Act: -0.1700
Data Index: 2173061 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.3850. Min Act: -0.1700
Data Index: 5504007 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.3850. Min Act: -0.1700
Data Index: 1302682 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.3538. Min Act: -0.1700
Data Index: 4194685 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9788. Min Range: -6.9788
Max Act: 6.3225. Min Act: -0.1700
Data Index: 6424992 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19