Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7767. Min Act: -0.1700
Data Index: 3477884 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7141. Min Act: -0.1700
Data Index: 1710142 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6829. Min Act: -0.1700
Data Index: 1469318 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6829. Min Act: -0.1700
Data Index: 1561569 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 6143538 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 165781 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 8355755 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 165783 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 6143542 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 6430967 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5420. Min Act: -0.1700
Data Index: 885751 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5420. Min Act: -0.1700
Data Index: 6236614 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 2963338 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5420. Min Act: -0.1700
Data Index: 6138251 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 7736882 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 2049095 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 6430968 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5107. Min Act: -0.1700
Data Index: 8730352 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4950. Min Act: -0.1700
Data Index: 6236612 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.4950. Min Act: -0.1700
Data Index: 2904180 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19