Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.6576. Min Act: -0.1700
Data Index: 4287349 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.5014. Min Act: -0.1700
Data Index: 3811220 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.4701. Min Act: -0.1700
Data Index: 2871515 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.4076. Min Act: -0.1700
Data Index: 6069155 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.3764. Min Act: -0.1700
Data Index: 4105787 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.3764. Min Act: -0.1700
Data Index: 5508986 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.3764. Min Act: -0.1700
Data Index: 8322595 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.3764. Min Act: -0.1700
Data Index: 7916151 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.4076. Min Act: -0.1700
Data Index: 6622140 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.3451. Min Act: -0.1700
Data Index: 3737920 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.2826. Min Act: -0.1700
Data Index: 3143531 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.2514. Min Act: -0.1700
Data Index: 1824927 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.2201. Min Act: -0.1700
Data Index: 6555667 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.2201. Min Act: -0.1700
Data Index: 804330 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.2201. Min Act: -0.1700
Data Index: 8697305 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.2514. Min Act: -0.1700
Data Index: 5430578 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.1889. Min Act: -0.1700
Data Index: 4434859 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.1889. Min Act: -0.1700
Data Index: 8110198 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.1889. Min Act: -0.1700
Data Index: 5605979 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6576. Min Range: -7.6576
Max Act: 7.1576. Min Act: -0.1700
Data Index: 5196573 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19