Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5749 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.3577. Min Act: -0.1700
Data Index: 4111601 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.3577. Min Act: -0.1700
Data Index: 4471023 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.3265. Min Act: -0.1700
Data Index: 3938328 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.3265. Min Act: -0.1700
Data Index: 3070063 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.3265. Min Act: -0.1700
Data Index: 7561290 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.2327. Min Act: -0.1700
Data Index: 3902573 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1702. Min Act: -0.1700
Data Index: 398576 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1702. Min Act: -0.1700
Data Index: 5902060 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1702. Min Act: -0.1700
Data Index: 4297067 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1702. Min Act: -0.1700
Data Index: 7065367 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1077. Min Act: -0.1700
Data Index: 864002 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1077. Min Act: -0.1700
Data Index: 3523933 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1077. Min Act: -0.1700
Data Index: 3523934 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.1077. Min Act: -0.1700
Data Index: 6419935 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.0764. Min Act: -0.1700
Data Index: 3523947 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.0764. Min Act: -0.1700
Data Index: 5783632 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.0764. Min Act: -0.1700
Data Index: 8765148 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.0764. Min Act: -0.1700
Data Index: 3523931 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.0764. Min Act: -0.1700
Data Index: 8628881 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3577. Min Range: -4.3577
Max Act: 4.0139. Min Act: -0.1700
Data Index: 6750653 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19