Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1663. Min Range: -6.1663
Max Act: 6.1663. Min Act: -0.1700
Data Index: 5877716 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1663. Min Range: -6.1663
Max Act: 6.1038. Min Act: -0.1700
Data Index: 5507148 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1663. Min Range: -6.1663
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3297753 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1663. Min Range: -6.1663
Max Act: 6.0101. Min Act: -0.1700
Data Index: 3106080 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1663. Min Range: -6.1663
Max Act: 6.0101. Min Act: -0.1700
Data Index: 2987829 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9788. Min Act: -0.1700
Data Index: 419863 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9788. Min Act: -0.1700
Data Index: 5172053 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9476. Min Act: -0.1700
Data Index: 2781103 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9476. Min Act: -0.1700
Data Index: 2036718 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9476. Min Act: -0.1700
Data Index: 7798082 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9163. Min Act: -0.1700
Data Index: 7362384 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9476. Min Act: -0.1700
Data Index: 3660313 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.9163. Min Act: -0.1700
Data Index: 6914360 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8851. Min Act: -0.1700
Data Index: 3162496 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8538. Min Act: -0.1700
Data Index: 3681939 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8226. Min Act: -0.1700
Data Index: 1570665 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8538. Min Act: -0.1700
Data Index: 2024795 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8226. Min Act: -0.1700
Data Index: 2464050 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8226. Min Act: -0.1700
Data Index: 1635509 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1663. Min Range: -6.1663
Max Act: 5.8226. Min Act: -0.1700
Data Index: 4332850 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19