Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.7946. Min Act: -0.1700
Data Index: 5887262 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.6696. Min Act: -0.1700
Data Index: 138955 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.6696. Min Act: -0.1700
Data Index: 3797071 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.6696. Min Act: -0.1700
Data Index: 7511332 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.6071. Min Act: -0.1700
Data Index: 8009129 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.6071. Min Act: -0.1700
Data Index: 5347622 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.5446. Min Act: -0.1700
Data Index: 4288078 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.5446. Min Act: -0.1700
Data Index: 4822735 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.5446. Min Act: -0.1700
Data Index: 5375815 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.5446. Min Act: -0.1700
Data Index: 7186549 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4821. Min Act: -0.1700
Data Index: 7602310 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4821. Min Act: -0.1700
Data Index: 7995237 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4821. Min Act: -0.1700
Data Index: 3408611 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4821. Min Act: -0.1700
Data Index: 2265133 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4196. Min Act: -0.1700
Data Index: 869565 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4196. Min Act: -0.1700
Data Index: 16388 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.4196. Min Act: -0.1700
Data Index: 6107800 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.3571. Min Act: -0.1700
Data Index: 349882 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.3571. Min Act: -0.1700
Data Index: 6215463 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7946. Min Range: -8.7946
Max Act: 8.3571. Min Act: -0.1700
Data Index: 3034244 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19