Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 365 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1363. Min Range: -2.1363
Max Act: 2.1363. Min Act: -0.1700
Data Index: 3720414 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1363. Min Range: -2.1363
Max Act: 2.0861. Min Act: -0.1700
Data Index: 3521906 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1363. Min Range: -2.1363
Max Act: 2.0525. Min Act: -0.1700
Data Index: 6261385 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1363. Min Range: -2.1363
Max Act: 2.0189. Min Act: -0.1700
Data Index: 2253361 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9851. Min Act: -0.1700
Data Index: 7702071 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9851. Min Act: -0.1700
Data Index: 8133863 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9851. Min Act: -0.1700
Data Index: 1297174 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9681. Min Act: -0.1700
Data Index: 8034621 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9681. Min Act: -0.1700
Data Index: 203206 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9681. Min Act: -0.1700
Data Index: 5529878 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9512. Min Act: -0.1700
Data Index: 7304988 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9681. Min Act: -0.1700
Data Index: 6349022 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9512. Min Act: -0.1700
Data Index: 2171008 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9342. Min Act: -0.1700
Data Index: 5461523 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9342. Min Act: -0.1700
Data Index: 4154473 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9172. Min Act: -0.1700
Data Index: 4328728 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9172. Min Act: -0.1700
Data Index: 153236 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9172. Min Act: -0.1700
Data Index: 7452844 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9172. Min Act: -0.1700
Data Index: 4534488 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1363. Min Range: -2.1363
Max Act: 1.9172. Min Act: -0.1700
Data Index: 7622679 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19