Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 868 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.6644. Min Act: -0.1700
Data Index: 8026248 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.5548. Min Act: -0.1700
Data Index: 369587 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.5235. Min Act: -0.1700
Data Index: 4197994 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.5235. Min Act: -0.1700
Data Index: 1482779 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3901364 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.5079. Min Act: -0.1700
Data Index: 7869496 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4609. Min Act: -0.1700
Data Index: 1331635 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4452. Min Act: -0.1700
Data Index: 5319868 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4295. Min Act: -0.1700
Data Index: 7740157 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4452. Min Act: -0.1700
Data Index: 3068254 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4452. Min Act: -0.1700
Data Index: 196386 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4452. Min Act: -0.1700
Data Index: 2787420 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4295. Min Act: -0.1700
Data Index: 2296835 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4295. Min Act: -0.1700
Data Index: 4345737 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4138. Min Act: -0.1700
Data Index: 8205363 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4138. Min Act: -0.1700
Data Index: 8744401 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.4138. Min Act: -0.1700
Data Index: 8567751 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.3982. Min Act: -0.1700
Data Index: 3829196 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.3825. Min Act: -0.1700
Data Index: 653929 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6644. Min Range: -3.6644
Max Act: 3.3982. Min Act: -0.1700
Data Index: 7634062 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19