Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5547 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2154. Min Range: -6.2154
Max Act: 6.2154. Min Act: -0.1700
Data Index: 6125498 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2154. Min Range: -6.2154
Max Act: 6.2154. Min Act: -0.1700
Data Index: 399904 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2154. Min Range: -6.2154
Max Act: 6.1529. Min Act: -0.1700
Data Index: 2257378 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2154. Min Range: -6.2154
Max Act: 6.0279. Min Act: -0.1700
Data Index: 8099230 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.9966. Min Act: -0.1700
Data Index: 5527973 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.9654. Min Act: -0.1700
Data Index: 1739927 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.9029. Min Act: -0.1700
Data Index: 653663 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.8404. Min Act: -0.1700
Data Index: 8720116 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.8091. Min Act: -0.1700
Data Index: 1470901 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7779. Min Act: -0.1700
Data Index: 292393 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7779. Min Act: -0.1700
Data Index: 3031011 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7779. Min Act: -0.1700
Data Index: 4422648 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7466. Min Act: -0.1700
Data Index: 5697855 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7466. Min Act: -0.1700
Data Index: 868033 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7779. Min Act: -0.1700
Data Index: 1226899 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.7154. Min Act: -0.1700
Data Index: 2348627 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.6841. Min Act: -0.1700
Data Index: 5281935 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.6841. Min Act: -0.1700
Data Index: 3338302 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.6841. Min Act: -0.1700
Data Index: 1261663 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2154. Min Range: -6.2154
Max Act: 5.6841. Min Act: -0.1700
Data Index: 4137150 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19