Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.5127. Min Act: -0.1700
Data Index: 4594453 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.4189. Min Act: -0.1700
Data Index: 152065 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.3877. Min Act: -0.1700
Data Index: 4454588 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.3877. Min Act: -0.1700
Data Index: 1758890 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2939. Min Act: -0.1700
Data Index: 3277053 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2939. Min Act: -0.1700
Data Index: 750534 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2627. Min Act: -0.1700
Data Index: 5546144 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2627. Min Act: -0.1700
Data Index: 5688954 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2314. Min Act: -0.1700
Data Index: 263486 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2627. Min Act: -0.1700
Data Index: 8096120 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2314. Min Act: -0.1700
Data Index: 5368620 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2314. Min Act: -0.1700
Data Index: 6477090 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2002. Min Act: -0.1700
Data Index: 7583640 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2002. Min Act: -0.1700
Data Index: 6893530 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2002. Min Act: -0.1700
Data Index: 2007720 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2002. Min Act: -0.1700
Data Index: 1019612 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.2002. Min Act: -0.1700
Data Index: 1593838 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.1689. Min Act: -0.1700
Data Index: 3184268 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.1377. Min Act: -0.1700
Data Index: 228929 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5127. Min Range: -5.5127
Max Act: 5.1689. Min Act: -0.1700
Data Index: 5506041 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19