Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4914 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3070. Min Range: -12.3070
Max Act: 12.3070. Min Act: -0.1700
Data Index: 3133813 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3070. Min Range: -12.3070
Max Act: 12.1195. Min Act: -0.1700
Data Index: 5256190 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3070. Min Range: -12.3070
Max Act: 12.0570. Min Act: -0.1700
Data Index: 2977678 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.9945. Min Act: -0.1700
Data Index: 2700948 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.9945. Min Act: -0.1700
Data Index: 8667458 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.9945. Min Act: -0.1700
Data Index: 2700946 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.8695. Min Act: -0.1700
Data Index: 5138706 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.8070. Min Act: -0.1700
Data Index: 2700949 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.8070. Min Act: -0.1700
Data Index: 6611103 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.8070. Min Act: -0.1700
Data Index: 1605477 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.7445. Min Act: -0.1700
Data Index: 4037450 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.7445. Min Act: -0.1700
Data Index: 8740706 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.6820. Min Act: -0.1700
Data Index: 8181369 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.5570. Min Act: -0.1700
Data Index: 4112109 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.4320. Min Act: -0.1700
Data Index: 6753727 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.4320. Min Act: -0.1700
Data Index: 5143425 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.4320. Min Act: -0.1700
Data Index: 6187585 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.3695. Min Act: -0.1700
Data Index: 7539369 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.3695. Min Act: -0.1700
Data Index: 2700950 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3070. Min Range: -12.3070
Max Act: 11.3070. Min Act: -0.1700
Data Index: 7858584 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19