Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.4359. Min Act: -0.1700
Data Index: 7370661 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.4359. Min Act: -0.1700
Data Index: 5898387 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.4359. Min Act: -0.1700
Data Index: 3926218 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.4359. Min Act: -0.1700
Data Index: 282726 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.4046. Min Act: -0.1700
Data Index: 3090588 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.4046. Min Act: -0.1700
Data Index: 6456686 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.3109. Min Act: -0.1700
Data Index: 2054458 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.3109. Min Act: -0.1700
Data Index: 7144607 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.3109. Min Act: -0.1700
Data Index: 7408530 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.3109. Min Act: -0.1700
Data Index: 7495945 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2796. Min Act: -0.1700
Data Index: 6864531 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2796. Min Act: -0.1700
Data Index: 4605190 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2796. Min Act: -0.1700
Data Index: 3489170 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2484. Min Act: -0.1700
Data Index: 8717163 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2484. Min Act: -0.1700
Data Index: 1500139 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2484. Min Act: -0.1700
Data Index: 464472 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2171. Min Act: -0.1700
Data Index: 5708649 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2171. Min Act: -0.1700
Data Index: 485514 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2171. Min Act: -0.1700
Data Index: 2445754 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4359. Min Range: -4.4359
Max Act: 4.2171. Min Act: -0.1700
Data Index: 3853655 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19