Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.2984. Min Act: -0.1700
Data Index: 5703746 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.2046. Min Act: -0.1700
Data Index: 7232548 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2984. Min Range: -7.2984
Max Act: 7.0484. Min Act: -0.1700
Data Index: 2434188 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.9859. Min Act: -0.1700
Data Index: 1417333 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.9546. Min Act: -0.1700
Data Index: 3233797 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.9546. Min Act: -0.1700
Data Index: 146282 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8609. Min Act: -0.1700
Data Index: 7614765 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8609. Min Act: -0.1700
Data Index: 714611 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8296. Min Act: -0.1700
Data Index: 1472969 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8296. Min Act: -0.1700
Data Index: 5820739 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 2097872 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.8296. Min Act: -0.1700
Data Index: 6679617 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 7769907 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 2144646 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7359. Min Act: -0.1700
Data Index: 2317155 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.7359. Min Act: -0.1700
Data Index: 7030128 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.6734. Min Act: -0.1700
Data Index: 7257322 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.6109. Min Act: -0.1700
Data Index: 860156 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.5796. Min Act: -0.1700
Data Index: 6777670 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2984. Min Range: -7.2984
Max Act: 6.5796. Min Act: -0.1700
Data Index: 4713376 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19