Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.8580. Min Act: -0.1700
Data Index: 7846669 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.6080. Min Act: -0.1700
Data Index: 5329790 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.3580. Min Act: -0.1700
Data Index: 5702979 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.1705. Min Act: -0.1700
Data Index: 5171344 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.1080. Min Act: -0.1700
Data Index: 315084 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.0455. Min Act: -0.1700
Data Index: 1143622 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8580. Min Range: -9.8580
Max Act: 9.1080. Min Act: -0.1700
Data Index: 6156704 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9830. Min Act: -0.1700
Data Index: 8459522 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9830. Min Act: -0.1700
Data Index: 48051 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9205. Min Act: -0.1700
Data Index: 1558938 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9205. Min Act: -0.1700
Data Index: 1100793 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9205. Min Act: -0.1700
Data Index: 6491921 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.8580. Min Act: -0.1700
Data Index: 347545 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9205. Min Act: -0.1700
Data Index: 5976444 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.9205. Min Act: -0.1700
Data Index: 1720431 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.8580. Min Act: -0.1700
Data Index: 4261716 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.7955. Min Act: -0.1700
Data Index: 7765221 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.7955. Min Act: -0.1700
Data Index: 863118 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.7330. Min Act: -0.1700
Data Index: 5990332 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8580. Min Range: -9.8580
Max Act: 8.7330. Min Act: -0.1700
Data Index: 2457116 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19