Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4307 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0891. Min Range: -7.0891
Max Act: 7.0891. Min Act: -0.1700
Data Index: 6629173 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.6203. Min Act: -0.1700
Data Index: 7865625 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.4953. Min Act: -0.1700
Data Index: 4622447 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.4641. Min Act: -0.1700
Data Index: 2153236 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.4641. Min Act: -0.1700
Data Index: 7388340 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.4328. Min Act: -0.1700
Data Index: 6743356 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.3703. Min Act: -0.1700
Data Index: 1695571 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.2766. Min Act: -0.1700
Data Index: 2874873 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.2141. Min Act: -0.1700
Data Index: 8200584 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.2141. Min Act: -0.1700
Data Index: 3858580 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.1516. Min Act: -0.1700
Data Index: 79733 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.1828. Min Act: -0.1700
Data Index: 2232730 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.1516. Min Act: -0.1700
Data Index: 1788769 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.1516. Min Act: -0.1700
Data Index: 4540123 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.0891. Min Act: -0.1700
Data Index: 4449547 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.1203. Min Act: -0.1700
Data Index: 6036800 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.0891. Min Act: -0.1700
Data Index: 2970388 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.0891. Min Act: -0.1700
Data Index: 3137376 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.0578. Min Act: -0.1700
Data Index: 6143756 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0891. Min Range: -7.0891
Max Act: 6.0578. Min Act: -0.1700
Data Index: 141379 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19