Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.8445. Min Act: -0.1700
Data Index: 2052075 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.5945. Min Act: -0.1700
Data Index: 776153 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.4070. Min Act: -0.1700
Data Index: 2655328 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.3445. Min Act: -0.1700
Data Index: 723749 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.2195. Min Act: -0.1700
Data Index: 7144009 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.1570. Min Act: -0.1700
Data Index: 3311891 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.1570. Min Act: -0.1700
Data Index: 3327562 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.1570. Min Act: -0.1700
Data Index: 5128010 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.1570. Min Act: -0.1700
Data Index: 7412221 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.1570. Min Act: -0.1700
Data Index: 2213797 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.0945. Min Act: -0.1700
Data Index: 1893835 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.0945. Min Act: -0.1700
Data Index: 3357525 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.0320. Min Act: -0.1700
Data Index: 3357541 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.0320. Min Act: -0.1700
Data Index: 3357550 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.0320. Min Act: -0.1700
Data Index: 3649069 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8445. Min Range: -11.8445
Max Act: 11.0945. Min Act: -0.1700
Data Index: 7797777 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8445. Min Range: -11.8445
Max Act: 10.9695. Min Act: -0.1700
Data Index: 3884809 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8445. Min Range: -11.8445
Max Act: 10.9695. Min Act: -0.1700
Data Index: 2464318 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8445. Min Range: -11.8445
Max Act: 10.9695. Min Act: -0.1700
Data Index: 4136619 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8445. Min Range: -11.8445
Max Act: 10.8445. Min Act: -0.1700
Data Index: 1435961 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19