Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.5432. Min Act: -0.1700
Data Index: 5208249 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.4494. Min Act: -0.1700
Data Index: 8196063 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.2932. Min Act: -0.1700
Data Index: 7788361 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.2307. Min Act: -0.1700
Data Index: 5889974 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.2307. Min Act: -0.1700
Data Index: 2959042 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.1369. Min Act: -0.1700
Data Index: 1350338 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.1057. Min Act: -0.1700
Data Index: 2775714 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.1057. Min Act: -0.1700
Data Index: 1533203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.0119. Min Act: -0.1700
Data Index: 1633044 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.0119. Min Act: -0.1700
Data Index: 7875711 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.0119. Min Act: -0.1700
Data Index: 7337776 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5432. Min Range: -5.5432
Max Act: 5.0119. Min Act: -0.1700
Data Index: 3673489 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.9494. Min Act: -0.1700
Data Index: 5466724 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.9807. Min Act: -0.1700
Data Index: 6111389 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.9494. Min Act: -0.1700
Data Index: 4205560 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.9494. Min Act: -0.1700
Data Index: 2541226 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.8869. Min Act: -0.1700
Data Index: 3690074 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.8869. Min Act: -0.1700
Data Index: 2890498 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.9182. Min Act: -0.1700
Data Index: 8443679 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5432. Min Range: -5.5432
Max Act: 4.8869. Min Act: -0.1700
Data Index: 4534331 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19