Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 2173163 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1699
Data Index: 7930027 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 7889695 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1699
Data Index: 7791848 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 7421614 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 7121484 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 7028865 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 6744521 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1699
Data Index: 2241764 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1695
Data Index: 5986464 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1696
Data Index: 140722 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 467742 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 1085786 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 5946858 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 5197853 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1699
Data Index: 2072283 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 4579552 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 2876522 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.6574. Min Act: -0.1700
Data Index: 11253 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6574. Min Range: -2.6574
Max Act: 2.5770. Min Act: -0.1699
Data Index: 5769061 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19