Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5623 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0943. Min Range: -6.0943
Max Act: 6.0943. Min Act: -0.1700
Data Index: 2180972 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0943. Min Range: -6.0943
Max Act: 6.0943. Min Act: -0.1700
Data Index: 120247 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0943. Min Range: -6.0943
Max Act: 6.0630. Min Act: -0.1700
Data Index: 6808172 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0943. Min Range: -6.0943
Max Act: 6.0318. Min Act: -0.1700
Data Index: 8096373 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0943. Min Range: -6.0943
Max Act: 6.0005. Min Act: -0.1700
Data Index: 7254192 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0943. Min Range: -6.0943
Max Act: 6.0005. Min Act: -0.1700
Data Index: 7253791 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9693. Min Act: -0.1700
Data Index: 5229387 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9693. Min Act: -0.1700
Data Index: 5031648 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9693. Min Act: -0.1700
Data Index: 8616754 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9068. Min Act: -0.1700
Data Index: 1715681 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9380. Min Act: -0.1700
Data Index: 456750 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9380. Min Act: -0.1700
Data Index: 6791171 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9380. Min Act: -0.1700
Data Index: 1745261 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9068. Min Act: -0.1700
Data Index: 1525878 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4971097 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.8755. Min Act: -0.1700
Data Index: 7056650 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.8755. Min Act: -0.1700
Data Index: 4184888 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.8755. Min Act: -0.1700
Data Index: 639462 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.8755. Min Act: -0.1700
Data Index: 7309097 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0943. Min Range: -6.0943
Max Act: 5.8443. Min Act: -0.1700
Data Index: 390687 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19