Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1492 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.7918. Min Act: -0.1700
Data Index: 4786199 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.7293. Min Act: -0.1700
Data Index: 2590154 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.6823. Min Act: -0.1700
Data Index: 5611027 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.6511. Min Act: -0.1700
Data Index: 5910517 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.6511. Min Act: -0.1700
Data Index: 5148047 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.5571. Min Act: -0.1700
Data Index: 672632 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.5415. Min Act: -0.1700
Data Index: 6962290 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.5415. Min Act: -0.1700
Data Index: 7197748 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.5258. Min Act: -0.1700
Data Index: 4464662 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4788. Min Act: -0.1700
Data Index: 5870082 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4788. Min Act: -0.1700
Data Index: 6436908 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4632. Min Act: -0.1700
Data Index: 7170306 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4318. Min Act: -0.1700
Data Index: 5266917 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4318. Min Act: -0.1700
Data Index: 1118642 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4318. Min Act: -0.1700
Data Index: 6637715 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4318. Min Act: -0.1700
Data Index: 5577931 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4005. Min Act: -0.1700
Data Index: 8349223 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.3848. Min Act: -0.1700
Data Index: 6678 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.4005. Min Act: -0.1700
Data Index: 7187647 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7918. Min Range: -3.7918
Max Act: 3.3848. Min Act: -0.1700
Data Index: 8010873 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19