Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.9479. Min Act: -0.1700
Data Index: 5429321 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.9792. Min Act: -0.1700
Data Index: 4534922 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.8854. Min Act: -0.1700
Data Index: 1193899 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.8229. Min Act: -0.1700
Data Index: 2626614 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.7292. Min Act: -0.1700
Data Index: 2576304 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.6667. Min Act: -0.1700
Data Index: 5331707 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.6667. Min Act: -0.1700
Data Index: 8394215 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.5417. Min Act: -0.1700
Data Index: 2096841 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.5417. Min Act: -0.1700
Data Index: 708885 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.5104. Min Act: -0.1700
Data Index: 8707494 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.5104. Min Act: -0.1700
Data Index: 8197825 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.4479. Min Act: -0.1700
Data Index: 8394217 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.3854. Min Act: -0.1700
Data Index: 708884 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.3229. Min Act: -0.1700
Data Index: 4039048 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.2917. Min Act: -0.1700
Data Index: 2379044 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.2604. Min Act: -0.1700
Data Index: 795358 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.2292. Min Act: -0.1700
Data Index: 211266 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.1979. Min Act: -0.1700
Data Index: 4833908 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.1979. Min Act: -0.1700
Data Index: 6779238 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9792. Min Range: -6.9792
Max Act: 6.1979. Min Act: -0.1700
Data Index: 7405198 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19