Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5416 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0947. Min Range: -6.0947
Max Act: 6.0947. Min Act: -0.1700
Data Index: 1201057 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.9072. Min Act: -0.1700
Data Index: 6055394 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.8760. Min Act: -0.1700
Data Index: 7183995 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.7822. Min Act: -0.1700
Data Index: 2305999 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.7822. Min Act: -0.1700
Data Index: 5731450 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 763334 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 5867163 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.7197. Min Act: -0.1700
Data Index: 7552358 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.6885. Min Act: -0.1700
Data Index: 7755816 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 3145829 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.6885. Min Act: -0.1700
Data Index: 5790749 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.6885. Min Act: -0.1700
Data Index: 5889686 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.6885. Min Act: -0.1700
Data Index: 6251261 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.6260. Min Act: -0.1700
Data Index: 3230130 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.5947. Min Act: -0.1700
Data Index: 487173 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.5947. Min Act: -0.1700
Data Index: 7142482 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.5947. Min Act: -0.1700
Data Index: 4860089 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.5947. Min Act: -0.1700
Data Index: 5563062 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.5947. Min Act: -0.1700
Data Index: 6750238 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0947. Min Range: -6.0947
Max Act: 5.5635. Min Act: -0.1700
Data Index: 143126 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19