Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.8728. Min Act: -0.1700
Data Index: 1607933 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4978. Min Act: -0.1700
Data Index: 7105008 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4665. Min Act: -0.1700
Data Index: 7250961 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4040. Min Act: -0.1700
Data Index: 4409494 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3728. Min Act: -0.1700
Data Index: 3414754 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3728. Min Act: -0.1700
Data Index: 8018614 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 8324621 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 8381150 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 4830817 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.2790. Min Act: -0.1700
Data Index: 7075578 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.2790. Min Act: -0.1700
Data Index: 4575962 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.2478. Min Act: -0.1700
Data Index: 8645435 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.2478. Min Act: -0.1700
Data Index: 1780016 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.2478. Min Act: -0.1700
Data Index: 3467664 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.1853. Min Act: -0.1700
Data Index: 8321342 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.1540. Min Act: -0.1700
Data Index: 2343691 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.1853. Min Act: -0.1700
Data Index: 4621877 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.1853. Min Act: -0.1700
Data Index: 7808550 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.2165. Min Act: -0.1700
Data Index: 4989351 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.1540. Min Act: -0.1700
Data Index: 1057494 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19