Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0533. Min Range: -5.0533
Max Act: 5.0533. Min Act: -0.1700
Data Index: 259430 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0533. Min Range: -5.0533
Max Act: 5.0221. Min Act: -0.1700
Data Index: 7158736 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.9596. Min Act: -0.1700
Data Index: 4705007 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.9283. Min Act: -0.1700
Data Index: 7906736 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.9596. Min Act: -0.1700
Data Index: 929914 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8971. Min Act: -0.1700
Data Index: 179035 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 597734 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8346. Min Act: -0.1700
Data Index: 5554077 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 5857545 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 6001220 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 8165181 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 1544216 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 6033844 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 4204913 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 6015166 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 7303775 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 2445571 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7096. Min Act: -0.1700
Data Index: 1453050 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7408. Min Act: -0.1700
Data Index: 3503718 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7408. Min Act: -0.1700
Data Index: 6728753 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19