Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5086 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.2696. Min Act: -0.1700
Data Index: 4495313 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.2696. Min Act: -0.1700
Data Index: 5582208 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1758. Min Act: -0.1700
Data Index: 8510275 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.2071. Min Act: -0.1700
Data Index: 7096343 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.2071. Min Act: -0.1700
Data Index: 7036364 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1446. Min Act: -0.1700
Data Index: 5845877 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1446. Min Act: -0.1700
Data Index: 6911787 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1758. Min Act: -0.1700
Data Index: 3215621 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1758. Min Act: -0.1700
Data Index: 4742093 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1446. Min Act: -0.1700
Data Index: 819332 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1133. Min Act: -0.1700
Data Index: 2103364 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 2693159 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 1285909 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 4298532 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.1133. Min Act: -0.1700
Data Index: 5455577 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 7759312 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 5807035 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 6311048 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0821. Min Act: -0.1700
Data Index: 6311038 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2696. Min Range: -5.2696
Max Act: 5.0508. Min Act: -0.1700
Data Index: 7413057 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19