Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.3725. Min Act: -0.1700
Data Index: 5195905 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.3725. Min Act: -0.1700
Data Index: 1259397 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.2475. Min Act: -0.1700
Data Index: 3600519 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.2162. Min Act: -0.1700
Data Index: 8055344 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.2162. Min Act: -0.1700
Data Index: 3805178 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.1850. Min Act: -0.1700
Data Index: 8242373 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.1537. Min Act: -0.1700
Data Index: 7707080 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.1850. Min Act: -0.1700
Data Index: 1278460 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.1850. Min Act: -0.1700
Data Index: 7442548 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.1850. Min Act: -0.1700
Data Index: 7158824 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.1537. Min Act: -0.1700
Data Index: 449628 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0912. Min Act: -0.1700
Data Index: 575698 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0912. Min Act: -0.1700
Data Index: 572349 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0600. Min Act: -0.1700
Data Index: 1981270 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0600. Min Act: -0.1700
Data Index: 3797682 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0600. Min Act: -0.1700
Data Index: 4189017 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0287. Min Act: -0.1700
Data Index: 1272879 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0287. Min Act: -0.1700
Data Index: 1595364 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3725. Min Range: -5.3725
Max Act: 5.0287. Min Act: -0.1700
Data Index: 5800758 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3725. Min Range: -5.3725
Max Act: 4.9662. Min Act: -0.1700
Data Index: 2273296 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19