Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.9271. Min Act: -0.1700
Data Index: 7346869 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.8333. Min Act: -0.1700
Data Index: 6510336 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.8333. Min Act: -0.1700
Data Index: 6490108 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7864. Min Act: -0.1700
Data Index: 3441464 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7708. Min Act: -0.1700
Data Index: 2463360 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7239. Min Act: -0.1700
Data Index: 2180031 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7239. Min Act: -0.1700
Data Index: 3819426 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7082. Min Act: -0.1700
Data Index: 7907947 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7082. Min Act: -0.1700
Data Index: 4466531 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.7082. Min Act: -0.1700
Data Index: 1063694 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.6769. Min Act: -0.1700
Data Index: 1885503 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.6769. Min Act: -0.1700
Data Index: 3393615 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.6613. Min Act: -0.1700
Data Index: 5998142 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.6456. Min Act: -0.1700
Data Index: 6057562 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.6456. Min Act: -0.1700
Data Index: 4960084 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.6143. Min Act: -0.1700
Data Index: 8454791 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.5987. Min Act: -0.1700
Data Index: 3054825 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.5987. Min Act: -0.1700
Data Index: 4796983 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.5830. Min Act: -0.1700
Data Index: 3949157 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9271. Min Range: -3.9271
Max Act: 3.5830. Min Act: -0.1700
Data Index: 231802 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19