Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.7305. Min Act: -0.1700
Data Index: 2821553 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.6992. Min Act: -0.1700
Data Index: 806078 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.6367. Min Act: -0.1700
Data Index: 7589323 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.6055. Min Act: -0.1700
Data Index: 74683 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.5430. Min Act: -0.1700
Data Index: 3274292 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.4805. Min Act: -0.1700
Data Index: 1107939 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.3555. Min Act: -0.1700
Data Index: 3951084 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2617. Min Act: -0.1700
Data Index: 1957202 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.3242. Min Act: -0.1700
Data Index: 7495469 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2617. Min Act: -0.1700
Data Index: 8230055 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2930. Min Act: -0.1700
Data Index: 4831720 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2617. Min Act: -0.1700
Data Index: 4494646 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2930. Min Act: -0.1700
Data Index: 6746805 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2617. Min Act: -0.1700
Data Index: 2188722 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2305. Min Act: -0.1700
Data Index: 6077863 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.2617. Min Act: -0.1700
Data Index: 2690360 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.1992. Min Act: -0.1700
Data Index: 1193527 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.1992. Min Act: -0.1700
Data Index: 5330632 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.1680. Min Act: -0.1700
Data Index: 4076131 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7305. Min Range: -6.7305
Max Act: 6.1680. Min Act: -0.1700
Data Index: 956997 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19