Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.6962. Min Act: -0.1700
Data Index: 3198139 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.4462. Min Act: -0.1700
Data Index: 652419 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.1962. Min Act: -0.1700
Data Index: 8374611 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.1649. Min Act: -0.1700
Data Index: 5012168 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.1024. Min Act: -0.1700
Data Index: 4789976 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.1024. Min Act: -0.1700
Data Index: 999781 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.0712. Min Act: -0.1700
Data Index: 2790765 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.0399. Min Act: -0.1700
Data Index: 4525733 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6962. Min Range: -8.6962
Max Act: 8.0399. Min Act: -0.1700
Data Index: 2251257 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.9774. Min Act: -0.1700
Data Index: 7654108 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.9774. Min Act: -0.1700
Data Index: 2540713 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.9774. Min Act: -0.1700
Data Index: 7408764 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.9149. Min Act: -0.1700
Data Index: 790333 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8524. Min Act: -0.1700
Data Index: 628036 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8837. Min Act: -0.1700
Data Index: 334237 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8837. Min Act: -0.1700
Data Index: 5015350 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8837. Min Act: -0.1700
Data Index: 7401834 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8524. Min Act: -0.1700
Data Index: 5365525 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8524. Min Act: -0.1700
Data Index: 100984 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6962. Min Range: -8.6962
Max Act: 7.8524. Min Act: -0.1700
Data Index: 6239674 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19