Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.4349. Min Act: -0.1700
Data Index: 8316820 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.4037. Min Act: -0.1700
Data Index: 993700 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.4037. Min Act: -0.1700
Data Index: 131027 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.4037. Min Act: -0.1700
Data Index: 3480471 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 4943104 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 1064911 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3412. Min Act: -0.1700
Data Index: 4065579 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 2353944 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 5721897 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 965915 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 468798 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 3400206 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 678833 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3724. Min Act: -0.1700
Data Index: 725293 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3412. Min Act: -0.1700
Data Index: 314773 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3412. Min Act: -0.1700
Data Index: 3400201 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3412. Min Act: -0.1700
Data Index: 5983781 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3099. Min Act: -0.1700
Data Index: 6947391 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3412. Min Act: -0.1700
Data Index: 3932702 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4349. Min Range: -6.4349
Max Act: 6.3412. Min Act: -0.1700
Data Index: 4374285 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19