Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 902 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6082. Min Range: -6.6082
Max Act: 6.6082. Min Act: -0.1700
Data Index: 6540139 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6082. Min Range: -6.6082
Max Act: 6.4519. Min Act: -0.1700
Data Index: 3487648 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6082. Min Range: -6.6082
Max Act: 6.2957. Min Act: -0.1700
Data Index: 4791669 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.9832. Min Act: -0.1700
Data Index: 1012424 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.9832. Min Act: -0.1700
Data Index: 935888 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.9519. Min Act: -0.1700
Data Index: 1308344 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7871541 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.8582. Min Act: -0.1700
Data Index: 2507828 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.8269. Min Act: -0.1700
Data Index: 4816516 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.7957. Min Act: -0.1700
Data Index: 6362646 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.7332. Min Act: -0.1700
Data Index: 2893286 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.7019. Min Act: -0.1700
Data Index: 7718108 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.7019. Min Act: -0.1700
Data Index: 4419955 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.6707. Min Act: -0.1700
Data Index: 3827353 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6850526 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.6082. Min Act: -0.1700
Data Index: 288351 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.6082. Min Act: -0.1700
Data Index: 7569508 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.5769. Min Act: -0.1700
Data Index: 154814 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.6082. Min Act: -0.1700
Data Index: 3526345 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6082. Min Range: -6.6082
Max Act: 5.6082. Min Act: -0.1700
Data Index: 3232716 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19