Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1866. Min Range: -12.1866
Max Act: 12.1866. Min Act: -0.1700
Data Index: 3671812 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.6241. Min Act: -0.1700
Data Index: 1159679 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.6241. Min Act: -0.1700
Data Index: 3759203 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.4366. Min Act: -0.1700
Data Index: 3759208 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.4991. Min Act: -0.1700
Data Index: 1159680 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3741. Min Act: -0.1700
Data Index: 3759179 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3741. Min Act: -0.1700
Data Index: 3759180 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3741. Min Act: -0.1700
Data Index: 3974497 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3741. Min Act: -0.1700
Data Index: 3759178 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3116. Min Act: -0.1700
Data Index: 1478471 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3116. Min Act: -0.1700
Data Index: 3759171 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3116. Min Act: -0.1700
Data Index: 3759190 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.2491. Min Act: -0.1700
Data Index: 3759177 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.2491. Min Act: -0.1700
Data Index: 3759170 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.1866. Min Act: -0.1700
Data Index: 3759194 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.2491. Min Act: -0.1700
Data Index: 3759172 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.2491. Min Act: -0.1700
Data Index: 514543 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.2491. Min Act: -0.1700
Data Index: 38554 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.2491. Min Act: -0.1700
Data Index: 3759189 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1866. Min Range: -12.1866
Max Act: 11.3116. Min Act: -0.1700
Data Index: 2753239 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19