Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5041 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0606. Min Range: -5.0606
Max Act: 5.0606. Min Act: -0.1700
Data Index: 4552697 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.9356. Min Act: -0.1700
Data Index: 2677516 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.9356. Min Act: -0.1700
Data Index: 911466 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.9043. Min Act: -0.1700
Data Index: 1043678 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.9043. Min Act: -0.1700
Data Index: 441538 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2190576 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8418. Min Act: -0.1700
Data Index: 8231308 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8731. Min Act: -0.1700
Data Index: 7953631 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8418. Min Act: -0.1700
Data Index: 441540 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8418. Min Act: -0.1700
Data Index: 4501119 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8418. Min Act: -0.1700
Data Index: 709220 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8418. Min Act: -0.1700
Data Index: 6765799 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8106. Min Act: -0.1700
Data Index: 3134261 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8418. Min Act: -0.1700
Data Index: 98057 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8106. Min Act: -0.1700
Data Index: 4211045 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.8106. Min Act: -0.1700
Data Index: 22107 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.7793. Min Act: -0.1700
Data Index: 6609564 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.7793. Min Act: -0.1700
Data Index: 6270868 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.7793. Min Act: -0.1700
Data Index: 6140520 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0606. Min Range: -5.0606
Max Act: 4.7481. Min Act: -0.1700
Data Index: 391701 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19