Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5963 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.7675. Min Act: -0.1700
Data Index: 4334431 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5800. Min Act: -0.1700
Data Index: 1572747 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5800. Min Act: -0.1700
Data Index: 3619712 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5487. Min Act: -0.1700
Data Index: 6580265 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5175. Min Act: -0.1700
Data Index: 4343681 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5175. Min Act: -0.1700
Data Index: 7979500 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5175. Min Act: -0.1700
Data Index: 4159281 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.5175. Min Act: -0.1700
Data Index: 3149806 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4862. Min Act: -0.1700
Data Index: 1150482 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 1923398 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 6888572 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 3321521 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 8486328 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 2060889 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 4156451 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 623039 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4237. Min Act: -0.1700
Data Index: 4079298 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4550. Min Act: -0.1700
Data Index: 7580070 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4237. Min Act: -0.1700
Data Index: 4186557 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7675. Min Range: -4.7675
Max Act: 4.4237. Min Act: -0.1700
Data Index: 1737937 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19