Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5632 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.8437. Min Act: -0.1700
Data Index: 3746234 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.6874. Min Act: -0.1700
Data Index: 6275141 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5935. Min Act: -0.1700
Data Index: 4011722 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.6248. Min Act: -0.1700
Data Index: 513884 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.6248. Min Act: -0.1700
Data Index: 3148418 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5935. Min Act: -0.1700
Data Index: 8753017 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5935. Min Act: -0.1700
Data Index: 6220344 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5935. Min Act: -0.1700
Data Index: 3390855 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5935. Min Act: -0.1700
Data Index: 1503815 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5935. Min Act: -0.1700
Data Index: 2071245 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5622. Min Act: -0.1700
Data Index: 2684218 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5622. Min Act: -0.1700
Data Index: 1404730 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5308. Min Act: -0.1700
Data Index: 5322534 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5308. Min Act: -0.1700
Data Index: 7323835 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5308. Min Act: -0.1700
Data Index: 7061090 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5622. Min Act: -0.1700
Data Index: 6632640 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5308. Min Act: -0.1700
Data Index: 5728289 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5308. Min Act: -0.1700
Data Index: 570958 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5622. Min Act: -0.1700
Data Index: 2558371 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8437. Min Range: -3.8437
Max Act: 3.5308. Min Act: -0.1700
Data Index: 5744542 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19