Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5128. Min Range: -5.5128
Max Act: 5.5128. Min Act: -0.1700
Data Index: 2909815 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5128. Min Range: -5.5128
Max Act: 5.5128. Min Act: -0.1700
Data Index: 3484525 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5128. Min Range: -5.5128
Max Act: 5.3878. Min Act: -0.1700
Data Index: 512661 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5128. Min Range: -5.5128
Max Act: 5.3565. Min Act: -0.1700
Data Index: 8212562 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5128. Min Range: -5.5128
Max Act: 5.1065. Min Act: -0.1700
Data Index: 1570809 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5128. Min Range: -5.5128
Max Act: 5.0440. Min Act: -0.1700
Data Index: 2853878 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9503. Min Act: -0.1700
Data Index: 172918 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9503. Min Act: -0.1700
Data Index: 1171720 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 6369140 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 7523799 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 3064689 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 6045532 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 5935210 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 4055814 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 3851798 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.9190. Min Act: -0.1700
Data Index: 8775043 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 2115274 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 543731 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 4568351 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5128. Min Range: -5.5128
Max Act: 4.8878. Min Act: -0.1700
Data Index: 6295979 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19