Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.2680. Min Act: -0.1700
Data Index: 5996935 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.2680. Min Act: -0.1700
Data Index: 5102102 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1742. Min Act: -0.1700
Data Index: 5180284 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1742. Min Act: -0.1700
Data Index: 3189288 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1430. Min Act: -0.1700
Data Index: 1276642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1430. Min Act: -0.1700
Data Index: 6667418 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1430. Min Act: -0.1700
Data Index: 7776452 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1117. Min Act: -0.1700
Data Index: 1773229 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1117. Min Act: -0.1700
Data Index: 3484568 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1117. Min Act: -0.1700
Data Index: 6630858 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1117. Min Act: -0.1700
Data Index: 8373565 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.1117. Min Act: -0.1700
Data Index: 2209498 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0804. Min Act: -0.1700
Data Index: 4024618 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0804. Min Act: -0.1700
Data Index: 2201856 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0804. Min Act: -0.1700
Data Index: 4938700 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0492. Min Act: -0.1700
Data Index: 7416220 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0804. Min Act: -0.1700
Data Index: 3484566 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0492. Min Act: -0.1700
Data Index: 4723625 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0492. Min Act: -0.1700
Data Index: 5179913 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2680. Min Range: -4.2680
Max Act: 4.0492. Min Act: -0.1700
Data Index: 5667911 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19