Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6121 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1571. Min Range: -5.1571
Max Act: 5.1571. Min Act: -0.1700
Data Index: 897650 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1571. Min Range: -5.1571
Max Act: 5.0321. Min Act: -0.1700
Data Index: 1345937 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.9071. Min Act: -0.1700
Data Index: 1247491 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.8446. Min Act: -0.1700
Data Index: 5106212 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.7509. Min Act: -0.1700
Data Index: 5599987 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.7821. Min Act: -0.1700
Data Index: 4932604 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.7509. Min Act: -0.1700
Data Index: 2178225 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6884. Min Act: -0.1700
Data Index: 3895638 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6884. Min Act: -0.1700
Data Index: 2556580 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6571. Min Act: -0.1700
Data Index: 2407119 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6571. Min Act: -0.1700
Data Index: 7334567 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5946. Min Act: -0.1700
Data Index: 8122209 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6259. Min Act: -0.1700
Data Index: 4812036 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5946. Min Act: -0.1700
Data Index: 8181711 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6259. Min Act: -0.1700
Data Index: 5709734 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6259. Min Act: -0.1700
Data Index: 4783584 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5634. Min Act: -0.1700
Data Index: 523623 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5946. Min Act: -0.1700
Data Index: 8353224 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5009. Min Act: -0.1700
Data Index: 7384374 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5009. Min Act: -0.1700
Data Index: 7932769 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19