Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4294 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1300. Min Range: -9.1300
Max Act: 9.1300. Min Act: -0.1700
Data Index: 5301587 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1300. Min Range: -9.1300
Max Act: 9.1300. Min Act: -0.1700
Data Index: 8621835 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1300. Min Range: -9.1300
Max Act: 9.0050. Min Act: -0.1700
Data Index: 608471 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.9425. Min Act: -0.1700
Data Index: 6185067 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.8800. Min Act: -0.1700
Data Index: 2036096 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.6925. Min Act: -0.1700
Data Index: 2350193 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.6925. Min Act: -0.1700
Data Index: 3037035 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.6300. Min Act: -0.1700
Data Index: 4649892 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.6300. Min Act: -0.1700
Data Index: 5721386 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.5050. Min Act: -0.1700
Data Index: 7775696 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.4425. Min Act: -0.1700
Data Index: 5881745 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.4425. Min Act: -0.1700
Data Index: 6144700 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3800. Min Act: -0.1700
Data Index: 3111203 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3800. Min Act: -0.1699
Data Index: 8670998 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3175. Min Act: -0.1700
Data Index: 47451 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3175. Min Act: -0.1700
Data Index: 7152879 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3175. Min Act: -0.1700
Data Index: 5509323 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3175. Min Act: -0.1700
Data Index: 8163845 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3175. Min Act: -0.1700
Data Index: 6090912 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1300. Min Range: -9.1300
Max Act: 8.3175. Min Act: -0.1700
Data Index: 5327096 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19