Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8942. Min Act: -0.1700
Data Index: 8334205 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.9255. Min Act: -0.1700
Data Index: 6398664 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8942. Min Act: -0.1700
Data Index: 438736 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8317. Min Act: -0.1700
Data Index: 6932869 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8630. Min Act: -0.1700
Data Index: 634932 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8005. Min Act: -0.1700
Data Index: 2503422 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8005. Min Act: -0.1700
Data Index: 336770 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.8005. Min Act: -0.1700
Data Index: 4407612 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7692. Min Act: -0.1700
Data Index: 2088130 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7692. Min Act: -0.1700
Data Index: 7074449 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7692. Min Act: -0.1700
Data Index: 7626243 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7692. Min Act: -0.1700
Data Index: 4018681 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7692. Min Act: -0.1700
Data Index: 422547 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7067. Min Act: -0.1700
Data Index: 4050195 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7067. Min Act: -0.1700
Data Index: 2376588 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.6755. Min Act: -0.1700
Data Index: 4407611 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7067. Min Act: -0.1700
Data Index: 174586 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7380. Min Act: -0.1700
Data Index: 2903512 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7067. Min Act: -0.1700
Data Index: 1203561 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9255. Min Range: -5.9255
Max Act: 5.7380. Min Act: -0.1700
Data Index: 5620225 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19