Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.7974. Min Act: -0.1700
Data Index: 5882567 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.5474. Min Act: -0.1700
Data Index: 2081948 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.2974. Min Act: -0.1700
Data Index: 6360467 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.2974. Min Act: -0.1700
Data Index: 3611197 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.2974. Min Act: -0.1700
Data Index: 2862786 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.2974. Min Act: -0.1700
Data Index: 2171189 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.1724. Min Act: -0.1700
Data Index: 2759653 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.1724. Min Act: -0.1700
Data Index: 8360484 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.1724. Min Act: -0.1700
Data Index: 2020085 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.0474. Min Act: -0.1700
Data Index: 2355283 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.0474. Min Act: -0.1700
Data Index: 5059517 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.7974. Min Range: -21.7974
Max Act: 21.0474. Min Act: -0.1700
Data Index: 1531983 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.9224. Min Act: -0.1700
Data Index: 7101574 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.7974. Min Act: -0.1700
Data Index: 8321320 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.7974. Min Act: -0.1700
Data Index: 4515256 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.7974. Min Act: -0.1700
Data Index: 5750276 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.7974. Min Act: -0.1700
Data Index: 3338042 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.9224. Min Act: -0.1700
Data Index: 1860049 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.7974. Min Act: -0.1700
Data Index: 1190219 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.7974. Min Range: -21.7974
Max Act: 20.6724. Min Act: -0.1700
Data Index: 6033493 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19