Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0419. Min Range: -8.0419
Max Act: 8.0419. Min Act: -0.1700
Data Index: 1710642 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.8232. Min Act: -0.1700
Data Index: 7090717 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.7294. Min Act: -0.1700
Data Index: 7160090 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.6982. Min Act: -0.1700
Data Index: 6473474 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.6669. Min Act: -0.1700
Data Index: 821099 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.6669. Min Act: -0.1700
Data Index: 262550 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.6357. Min Act: -0.1700
Data Index: 8133722 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.5732. Min Act: -0.1700
Data Index: 3636555 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.5419. Min Act: -0.1700
Data Index: 7243891 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.5107. Min Act: -0.1700
Data Index: 5280591 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.4794. Min Act: -0.1700
Data Index: 6457361 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.4794. Min Act: -0.1700
Data Index: 5516436 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.4482. Min Act: -0.1700
Data Index: 6971086 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.4482. Min Act: -0.1700
Data Index: 7682638 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.3544. Min Act: -0.1700
Data Index: 49342 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.3232. Min Act: -0.1700
Data Index: 5140388 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.3232. Min Act: -0.1700
Data Index: 1578693 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.3232. Min Act: -0.1700
Data Index: 3328868 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.3232. Min Act: -0.1700
Data Index: 5204195 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0419. Min Range: -8.0419
Max Act: 7.2919. Min Act: -0.1700
Data Index: 3004286 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19