Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 2530279 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1040. Min Act: -0.1700
Data Index: 4710838 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.0102. Min Act: -0.1700
Data Index: 7289145 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9477. Min Act: -0.1700
Data Index: 8532231 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9165. Min Act: -0.1700
Data Index: 7025912 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9165. Min Act: -0.1700
Data Index: 3129721 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 2445252 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8540. Min Act: -0.1700
Data Index: 7644485 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6827156 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7915. Min Act: -0.1700
Data Index: 1505962 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7290. Min Act: -0.1700
Data Index: 8237305 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8295577 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5453718 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 6740452 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 7061606 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5215053 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6665. Min Act: -0.1700
Data Index: 3651854 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6665. Min Act: -0.1700
Data Index: 5538884 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 8109968 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 773853 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19