Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0639. Min Range: -8.0639
Max Act: 8.0639. Min Act: -0.1700
Data Index: 7356932 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.6576. Min Act: -0.1700
Data Index: 416498 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.5326. Min Act: -0.1700
Data Index: 1053276 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.4076. Min Act: -0.1700
Data Index: 621089 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.3764. Min Act: -0.1700
Data Index: 8666570 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.4076. Min Act: -0.1700
Data Index: 7283492 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.3764. Min Act: -0.1700
Data Index: 5258250 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.3764. Min Act: -0.1700
Data Index: 2782499 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.3451. Min Act: -0.1700
Data Index: 1179858 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.3764. Min Act: -0.1700
Data Index: 8431167 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.2201. Min Act: -0.1700
Data Index: 7214627 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1889. Min Act: -0.1700
Data Index: 5153255 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1889. Min Act: -0.1700
Data Index: 4505771 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1576. Min Act: -0.1700
Data Index: 5126216 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1264. Min Act: -0.1700
Data Index: 3650793 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1264. Min Act: -0.1700
Data Index: 4177563 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1576. Min Act: -0.1700
Data Index: 4421906 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1576. Min Act: -0.1700
Data Index: 6870851 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.0951. Min Act: -0.1700
Data Index: 4245670 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0639. Min Range: -8.0639
Max Act: 7.1264. Min Act: -0.1700
Data Index: 4523341 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19