Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1732 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.7078. Min Act: -0.1700
Data Index: 5000098 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.6765. Min Act: -0.1700
Data Index: 77618 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.5515. Min Act: -0.1700
Data Index: 368796 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.5203. Min Act: -0.1700
Data Index: 8537191 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.5203. Min Act: -0.1700
Data Index: 5249100 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.4578. Min Act: -0.1700
Data Index: 8280254 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3953. Min Act: -0.1700
Data Index: 6453305 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3953. Min Act: -0.1700
Data Index: 2629572 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3953. Min Act: -0.1700
Data Index: 5578475 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.4265. Min Act: -0.1700
Data Index: 6271800 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3640. Min Act: -0.1700
Data Index: 4876414 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3640. Min Act: -0.1700
Data Index: 2823606 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3328. Min Act: -0.1700
Data Index: 3040612 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.3328. Min Act: -0.1700
Data Index: 3734541 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.2078. Min Act: -0.1700
Data Index: 3314493 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.2078. Min Act: -0.1700
Data Index: 2356963 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.2078. Min Act: -0.1700
Data Index: 1643780 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.1453. Min Act: -0.1700
Data Index: 5103136 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.1453. Min Act: -0.1700
Data Index: 6771108 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7078. Min Range: -6.7078
Max Act: 6.1453. Min Act: -0.1700
Data Index: 5010345 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19