Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.9587. Min Act: -0.1700
Data Index: 3133950 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8962. Min Act: -0.1700
Data Index: 179739 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8649. Min Act: -0.1700
Data Index: 3146684 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8649. Min Act: -0.1700
Data Index: 3128637 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8337. Min Act: -0.1700
Data Index: 2049054 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8337. Min Act: -0.1700
Data Index: 4039177 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8649. Min Act: -0.1700
Data Index: 4952562 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8024. Min Act: -0.1700
Data Index: 2797032 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8024. Min Act: -0.1700
Data Index: 4715566 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.8024. Min Act: -0.1700
Data Index: 134259 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.7399. Min Act: -0.1700
Data Index: 5068013 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.7712. Min Act: -0.1700
Data Index: 1324124 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.7399. Min Act: -0.1700
Data Index: 8706262 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.7087. Min Act: -0.1700
Data Index: 4648774 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.7087. Min Act: -0.1700
Data Index: 8729546 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.6774. Min Act: -0.1700
Data Index: 4456581 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.6774. Min Act: -0.1700
Data Index: 5360876 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.6774. Min Act: -0.1700
Data Index: 5399201 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.6462. Min Act: -0.1700
Data Index: 2844924 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9587. Min Range: -4.9587
Max Act: 4.6774. Min Act: -0.1700
Data Index: 3657410 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19