Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.9451. Min Act: -0.1700
Data Index: 5178683 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.9138. Min Act: -0.1700
Data Index: 4224830 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.7888. Min Act: -0.1700
Data Index: 8555598 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.7576. Min Act: -0.1700
Data Index: 7644501 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.7263. Min Act: -0.1700
Data Index: 6305490 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.7263. Min Act: -0.1700
Data Index: 2559808 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.6326. Min Act: -0.1700
Data Index: 140414 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.6013. Min Act: -0.1700
Data Index: 2069130 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6599330 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.5701. Min Act: -0.1700
Data Index: 363196 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.5701. Min Act: -0.1700
Data Index: 8106267 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.5076. Min Act: -0.1700
Data Index: 2507322 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4763. Min Act: -0.1700
Data Index: 4292845 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4763. Min Act: -0.1700
Data Index: 4423238 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4451. Min Act: -0.1700
Data Index: 3005603 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4451. Min Act: -0.1700
Data Index: 2900851 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4451. Min Act: -0.1700
Data Index: 7214788 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4763. Min Act: -0.1700
Data Index: 580238 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4451. Min Act: -0.1700
Data Index: 7508601 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9451. Min Range: -6.9451
Max Act: 6.4451. Min Act: -0.1700
Data Index: 4100385 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19