Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1452 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.2825. Min Act: -0.1700
Data Index: 3392093 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.1575. Min Act: -0.1700
Data Index: 526728 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.1262. Min Act: -0.1700
Data Index: 2385658 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.1575. Min Act: -0.1700
Data Index: 8254842 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.0637. Min Act: -0.1700
Data Index: 5477883 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.0637. Min Act: -0.1700
Data Index: 3481622 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.0325. Min Act: -0.1700
Data Index: 159285 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.0012. Min Act: -0.1700
Data Index: 6486027 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7870720 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9700. Min Act: -0.1700
Data Index: 2630868 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9700. Min Act: -0.1700
Data Index: 7796733 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9700. Min Act: -0.1700
Data Index: 7869684 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9387. Min Act: -0.1700
Data Index: 7561296 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9075. Min Act: -0.1700
Data Index: 2457526 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9387. Min Act: -0.1700
Data Index: 4379224 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8762. Min Act: -0.1700
Data Index: 5912048 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8450. Min Act: -0.1700
Data Index: 2112736 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8762. Min Act: -0.1700
Data Index: 269327 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8450. Min Act: -0.1700
Data Index: 1452226 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8450. Min Act: -0.1700
Data Index: 7979964 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19