Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4170 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7288. Min Range: -8.7288
Max Act: 8.7288. Min Act: -0.1700
Data Index: 5003123 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7288. Min Range: -8.7288
Max Act: 8.2913. Min Act: -0.1700
Data Index: 6766938 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7288. Min Range: -8.7288
Max Act: 8.3538. Min Act: -0.1700
Data Index: 4861882 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7288. Min Range: -8.7288
Max Act: 8.1038. Min Act: -0.1700
Data Index: 6749814 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9788. Min Act: -0.1700
Data Index: 1498637 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9788. Min Act: -0.1700
Data Index: 6764316 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9788. Min Act: -0.1700
Data Index: 8114099 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9163. Min Act: -0.1700
Data Index: 1813629 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9163. Min Act: -0.1700
Data Index: 544068 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9163. Min Act: -0.1700
Data Index: 5704623 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9163. Min Act: -0.1700
Data Index: 357915 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.9163. Min Act: -0.1700
Data Index: 5302112 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7913. Min Act: -0.1700
Data Index: 4965644 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7913. Min Act: -0.1700
Data Index: 47858 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7913. Min Act: -0.1700
Data Index: 1614629 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7913. Min Act: -0.1700
Data Index: 8662356 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7288. Min Act: -0.1700
Data Index: 7028769 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7288. Min Act: -0.1700
Data Index: 3972036 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7288. Min Act: -0.1700
Data Index: 8187801 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7288. Min Range: -8.7288
Max Act: 7.7288. Min Act: -0.1700
Data Index: 1882480 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19