Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4777 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.3778. Min Act: -0.1700
Data Index: 8472682 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.1903. Min Act: -0.1700
Data Index: 7498913 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.1278. Min Act: -0.1700
Data Index: 347124 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.1278. Min Act: -0.1700
Data Index: 81604 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.1278. Min Act: -0.1700
Data Index: 3370893 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.1278. Min Act: -0.1700
Data Index: 2938539 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.0653. Min Act: -0.1700
Data Index: 4817681 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.0028. Min Act: -0.1700
Data Index: 3064920 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.0028. Min Act: -0.1700
Data Index: 1139368 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.9403. Min Act: -0.1700
Data Index: 5532563 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.9403. Min Act: -0.1700
Data Index: 4240220 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.9403. Min Act: -0.1700
Data Index: 511414 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3778. Min Range: -9.3778
Max Act: 9.0028. Min Act: -0.1700
Data Index: 8704089 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8778. Min Act: -0.1700
Data Index: 351665 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8778. Min Act: -0.1700
Data Index: 8126380 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8778. Min Act: -0.1700
Data Index: 4634449 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8153. Min Act: -0.1700
Data Index: 7012168 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8778. Min Act: -0.1700
Data Index: 2290955 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8153. Min Act: -0.1700
Data Index: 56919 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3778. Min Range: -9.3778
Max Act: 8.8153. Min Act: -0.1700
Data Index: 8328626 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19