Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2253 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1720. Min Range: -6.1720
Max Act: 6.1720. Min Act: -0.1700
Data Index: 4981607 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1720. Min Range: -6.1720
Max Act: 6.0782. Min Act: -0.1700
Data Index: 5013940 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1720. Min Range: -6.1720
Max Act: 6.0782. Min Act: -0.1700
Data Index: 8721988 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.9845. Min Act: -0.1700
Data Index: 189075 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1720. Min Range: -6.1720
Max Act: 6.0157. Min Act: -0.1700
Data Index: 8705707 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.9845. Min Act: -0.1700
Data Index: 443540 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.9532. Min Act: -0.1700
Data Index: 1795418 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8907. Min Act: -0.1700
Data Index: 2477237 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.9220. Min Act: -0.1700
Data Index: 2749375 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.9220. Min Act: -0.1700
Data Index: 2529594 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8907. Min Act: -0.1700
Data Index: 1076847 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8907. Min Act: -0.1700
Data Index: 6011249 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8907. Min Act: -0.1700
Data Index: 6999138 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8907. Min Act: -0.1700
Data Index: 7522164 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8595. Min Act: -0.1700
Data Index: 7025452 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8595. Min Act: -0.1700
Data Index: 2608514 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8282. Min Act: -0.1700
Data Index: 461811 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8282. Min Act: -0.1700
Data Index: 8064506 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.8282. Min Act: -0.1700
Data Index: 8273529 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1720. Min Range: -6.1720
Max Act: 5.7970. Min Act: -0.1700
Data Index: 1447335 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19