Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5050 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.6082. Min Act: -0.1700
Data Index: 7063920 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.1707. Min Act: -0.1700
Data Index: 4226073 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.1082. Min Act: -0.1700
Data Index: 8532746 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.1082. Min Act: -0.1700
Data Index: 1352023 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.0457. Min Act: -0.1700
Data Index: 4912857 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.0457. Min Act: -0.1700
Data Index: 6473108 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6082. Min Range: -8.6082
Max Act: 8.0457. Min Act: -0.1700
Data Index: 2843203 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.9832. Min Act: -0.1700
Data Index: 2247652 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.9207. Min Act: -0.1700
Data Index: 461687 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 7636803 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.9207. Min Act: -0.1700
Data Index: 8339260 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.9207. Min Act: -0.1700
Data Index: 2243042 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 1830911 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.7957. Min Act: -0.1700
Data Index: 2077828 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 4606895 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 6031921 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 506592 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.7957. Min Act: -0.1700
Data Index: 2979492 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.7957. Min Act: -0.1700
Data Index: 5691197 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6082. Min Range: -8.6082
Max Act: 7.7957. Min Act: -0.1700
Data Index: 7464888 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19