Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 252 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.7314. Min Act: -0.1700
Data Index: 2729914 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.7314. Min Act: -0.1700
Data Index: 7831652 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.6689. Min Act: -0.1700
Data Index: 4930270 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.6689. Min Act: -0.1700
Data Index: 3956629 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.6064. Min Act: -0.1700
Data Index: 945728 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.6064. Min Act: -0.1700
Data Index: 2073791 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.5439. Min Act: -0.1700
Data Index: 4019142 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.4814. Min Act: -0.1700
Data Index: 1707544 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.4814. Min Act: -0.1700
Data Index: 1974866 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.4814. Min Act: -0.1700
Data Index: 6286770 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.4189. Min Act: -0.1700
Data Index: 8070525 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.4189. Min Act: -0.1700
Data Index: 764556 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.4189. Min Act: -0.1700
Data Index: 7829721 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.3564. Min Act: -0.1700
Data Index: 8111057 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.2939. Min Act: -0.1700
Data Index: 1404752 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.3564. Min Act: -0.1700
Data Index: 7126196 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.3564. Min Act: -0.1700
Data Index: 4915014 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.2939. Min Act: -0.1700
Data Index: 2036256 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.2939. Min Act: -0.1700
Data Index: 6850986 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7314. Min Range: -9.7314
Max Act: 9.2939. Min Act: -0.1700
Data Index: 4498866 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19