Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.1818. Min Act: -0.1700
Data Index: 1279435 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.1818. Min Act: -0.1700
Data Index: 4662607 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.1818. Min Act: -0.1700
Data Index: 781722 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.1652. Min Act: -0.1700
Data Index: 5238413 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0984. Min Act: -0.1700
Data Index: 3513877 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0984. Min Act: -0.1700
Data Index: 7603883 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0984. Min Act: -0.1698
Data Index: 5752139 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0480. Min Act: -0.1700
Data Index: 3046924 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0480. Min Act: -0.1700
Data Index: 3830830 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0480. Min Act: -0.1700
Data Index: 737929 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0480. Min Act: -0.1700
Data Index: 6292224 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0480. Min Act: -0.1700
Data Index: 698163 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0480. Min Act: -0.1700
Data Index: 5052734 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0312. Min Act: -0.1700
Data Index: 2070999 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0312. Min Act: -0.1700
Data Index: 8721752 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0312. Min Act: -0.1700
Data Index: 8401174 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0312. Min Act: -0.1700
Data Index: 3990745 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0312. Min Act: -0.1700
Data Index: 6663690 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1818. Min Range: -2.1818
Max Act: 2.0143. Min Act: -0.1700
Data Index: 6455034 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1818. Min Range: -2.1818
Max Act: 1.9975. Min Act: -0.1700
Data Index: 4673986 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19