Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6360 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6498. Min Range: -8.6498
Max Act: 8.6498. Min Act: -0.1700
Data Index: 7951145 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.9623. Min Act: -0.1700
Data Index: 2095620 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.8685. Min Act: -0.1700
Data Index: 3381666 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.6810. Min Act: -0.1700
Data Index: 5250885 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.4623. Min Act: -0.1700
Data Index: 5250886 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.3060. Min Act: -0.1700
Data Index: 6058285 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.3373. Min Act: -0.1700
Data Index: 6089341 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.3373. Min Act: -0.1700
Data Index: 2887175 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.2123. Min Act: -0.1700
Data Index: 6900039 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.1810. Min Act: -0.1700
Data Index: 6030177 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.2123. Min Act: -0.1700
Data Index: 355759 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.1498. Min Act: -0.1700
Data Index: 5260664 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.1810. Min Act: -0.1700
Data Index: 5943105 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.1185. Min Act: -0.1700
Data Index: 7268101 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.0873. Min Act: -0.1700
Data Index: 5141705 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.0560. Min Act: -0.1700
Data Index: 1601549 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.0873. Min Act: -0.1700
Data Index: 5707676 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.0873. Min Act: -0.1700
Data Index: 2040969 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.0560. Min Act: -0.1700
Data Index: 757476 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6498. Min Range: -8.6498
Max Act: 7.0248. Min Act: -0.1700
Data Index: 6032057 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19