Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4835 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1749. Min Range: -6.1749
Max Act: 6.1749. Min Act: -0.1700
Data Index: 2896966 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1749. Min Range: -6.1749
Max Act: 6.1749. Min Act: -0.1700
Data Index: 4407214 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1749. Min Range: -6.1749
Max Act: 6.0186. Min Act: -0.1700
Data Index: 3175059 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.8624. Min Act: -0.1700
Data Index: 4300831 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.8624. Min Act: -0.1700
Data Index: 2163491 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3444036 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 4208915 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 5691894 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3515475 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7999. Min Act: -0.1700
Data Index: 6401144 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7999. Min Act: -0.1700
Data Index: 879628 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7999. Min Act: -0.1700
Data Index: 3670178 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7374. Min Act: -0.1700
Data Index: 8412838 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7999. Min Act: -0.1700
Data Index: 7141931 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 5022893 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7686. Min Act: -0.1700
Data Index: 3372025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7061. Min Act: -0.1700
Data Index: 5424853 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7374. Min Act: -0.1700
Data Index: 8265281 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7374. Min Act: -0.1700
Data Index: 4544335 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1749. Min Range: -6.1749
Max Act: 5.7374. Min Act: -0.1700
Data Index: 5065208 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19