Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1410 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0490. Min Act: -0.1700
Data Index: 5640899 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0490. Min Act: -0.1700
Data Index: 2016931 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0178. Min Act: -0.1700
Data Index: 4980819 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0178. Min Act: -0.1700
Data Index: 711278 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0490. Min Range: -5.0490
Max Act: 5.0178. Min Act: -0.1700
Data Index: 1953934 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9553. Min Act: -0.1700
Data Index: 4721532 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9865. Min Act: -0.1700
Data Index: 5350073 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9553. Min Act: -0.1700
Data Index: 1564199 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9553. Min Act: -0.1700
Data Index: 7742940 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9240. Min Act: -0.1700
Data Index: 8801266 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9240. Min Act: -0.1700
Data Index: 4135763 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9240. Min Act: -0.1700
Data Index: 5350072 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9240. Min Act: -0.1700
Data Index: 1536034 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.9240. Min Act: -0.1700
Data Index: 7601721 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8615. Min Act: -0.1700
Data Index: 2798449 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8928. Min Act: -0.1700
Data Index: 1957619 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8928. Min Act: -0.1700
Data Index: 3872662 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8928. Min Act: -0.1700
Data Index: 2770640 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8615. Min Act: -0.1700
Data Index: 5662756 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0490. Min Range: -5.0490
Max Act: 4.8615. Min Act: -0.1700
Data Index: 5454603 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19