Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.7748. Min Act: -0.1700
Data Index: 6367302 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.5873. Min Act: -0.1700
Data Index: 2356750 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.2748. Min Act: -0.1700
Data Index: 6152699 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.1498. Min Act: -0.1700
Data Index: 1530165 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.1498. Min Act: -0.1700
Data Index: 7489574 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.1498. Min Act: -0.1700
Data Index: 7928256 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.0873. Min Act: -0.1700
Data Index: 3879850 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.0873. Min Act: -0.1700
Data Index: 4109743 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.0248. Min Act: -0.1700
Data Index: 2007731 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.0248. Min Act: -0.1700
Data Index: 3988525 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.0248. Min Act: -0.1700
Data Index: 8697667 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7748. Min Range: -8.7748
Max Act: 8.0873. Min Act: -0.1700
Data Index: 1957937 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 2450569 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 5693531 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 1644329 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 8444609 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 395142 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 6021701 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.8998. Min Act: -0.1700
Data Index: 7535738 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7748. Min Range: -8.7748
Max Act: 7.9623. Min Act: -0.1700
Data Index: 261640 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19