Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.7996. Min Act: -0.1700
Data Index: 1727272 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.7683. Min Act: -0.1700
Data Index: 3689709 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1019214 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.7058. Min Act: -0.1700
Data Index: 7558107 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6746. Min Act: -0.1700
Data Index: 7048669 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6746. Min Act: -0.1700
Data Index: 2744058 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6433. Min Act: -0.1700
Data Index: 2992707 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6433. Min Act: -0.1700
Data Index: 7647856 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6121. Min Act: -0.1700
Data Index: 4393502 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6121. Min Act: -0.1700
Data Index: 6458021 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1019213 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5808. Min Act: -0.1700
Data Index: 4058614 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5808. Min Act: -0.1700
Data Index: 2493140 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5496. Min Act: -0.1700
Data Index: 4255237 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5808. Min Act: -0.1700
Data Index: 1582711 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5808. Min Act: -0.1700
Data Index: 453060 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5496. Min Act: -0.1700
Data Index: 5455018 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5183. Min Act: -0.1700
Data Index: 8643238 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5496. Min Act: -0.1700
Data Index: 6073122 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7996. Min Range: -5.7996
Max Act: 5.5496. Min Act: -0.1700
Data Index: 4892438 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19