Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5839 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1409. Min Range: -8.1409
Max Act: 8.1409. Min Act: -0.1700
Data Index: 2847168 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1409. Min Range: -8.1409
Max Act: 8.1409. Min Act: -0.1700
Data Index: 677847 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.8909. Min Act: -0.1700
Data Index: 2802465 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.8284. Min Act: -0.1700
Data Index: 2682915 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.7034. Min Act: -0.1700
Data Index: 3164432 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.6409. Min Act: -0.1700
Data Index: 1303468 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.6409. Min Act: -0.1700
Data Index: 5899787 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.5784. Min Act: -0.1700
Data Index: 931259 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.5784. Min Act: -0.1700
Data Index: 133169 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.5472. Min Act: -0.1700
Data Index: 4574586 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.5159. Min Act: -0.1700
Data Index: 3223719 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.5159. Min Act: -0.1700
Data Index: 193721 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4847. Min Act: -0.1700
Data Index: 1717846 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4534. Min Act: -0.1700
Data Index: 2120654 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4534. Min Act: -0.1700
Data Index: 1518615 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4534. Min Act: -0.1700
Data Index: 7658321 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4222. Min Act: -0.1700
Data Index: 4558403 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4222. Min Act: -0.1700
Data Index: 779122 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4222. Min Act: -0.1700
Data Index: 6328392 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1409. Min Range: -8.1409
Max Act: 7.4222. Min Act: -0.1700
Data Index: 4055796 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19