Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.7500. Min Act: -0.1700
Data Index: 8233947 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.5000. Min Act: -0.1700
Data Index: 697949 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.3750. Min Act: -0.1700
Data Index: 3594169 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.3750. Min Act: -0.1700
Data Index: 6267917 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.2812. Min Act: -0.1700
Data Index: 6040074 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.3125. Min Act: -0.1700
Data Index: 3203759 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.2812. Min Act: -0.1700
Data Index: 6541784 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.2812. Min Act: -0.1700
Data Index: 2909578 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1250. Min Act: -0.1700
Data Index: 3352312 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1562. Min Act: -0.1700
Data Index: 8430714 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1250. Min Act: -0.1700
Data Index: 3770134 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1250. Min Act: -0.1700
Data Index: 599810 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1250. Min Act: -0.1700
Data Index: 1208776 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1250. Min Act: -0.1700
Data Index: 4765470 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.1250. Min Act: -0.1700
Data Index: 832413 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.0937. Min Act: -0.1700
Data Index: 4640793 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.0625. Min Act: -0.1700
Data Index: 1013666 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.0000. Min Act: -0.1700
Data Index: 7944679 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.0312. Min Act: -0.1700
Data Index: 3090258 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7500. Min Range: -7.7500
Max Act: 7.0312. Min Act: -0.1700
Data Index: 4768731 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19