Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.4092. Min Act: -0.1700
Data Index: 1252998 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.4092. Min Act: -0.1700
Data Index: 6850875 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.2529. Min Act: -0.1700
Data Index: 5615462 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.2529. Min Act: -0.1700
Data Index: 6250615 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.2842. Min Act: -0.1700
Data Index: 7779802 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.2217. Min Act: -0.1700
Data Index: 4349501 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.1904. Min Act: -0.1700
Data Index: 1526266 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.1904. Min Act: -0.1700
Data Index: 5989149 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 194777 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 6294510 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.1279. Min Act: -0.1700
Data Index: 1499006 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0967. Min Act: -0.1700
Data Index: 7648208 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0654. Min Act: -0.1700
Data Index: 5030566 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0342. Min Act: -0.1700
Data Index: 353918 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0654. Min Act: -0.1700
Data Index: 46869 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0342. Min Act: -0.1700
Data Index: 2655460 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0342. Min Act: -0.1700
Data Index: 2031968 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0342. Min Act: -0.1700
Data Index: 611338 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0342. Min Act: -0.1700
Data Index: 3668950 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4092. Min Range: -5.4092
Max Act: 5.0029. Min Act: -0.1700
Data Index: 611517 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19