Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2150 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0583. Min Range: -8.0583
Max Act: 8.0583. Min Act: -0.1700
Data Index: 5861223 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.9958. Min Act: -0.1700
Data Index: 2860477 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.9958. Min Act: -0.1700
Data Index: 5972559 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.9958. Min Act: -0.1700
Data Index: 1100036 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.8708. Min Act: -0.1700
Data Index: 7031280 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.8708. Min Act: -0.1700
Data Index: 1359759 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.8708. Min Act: -0.1700
Data Index: 6007276 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.8708. Min Act: -0.1700
Data Index: 2726545 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.8083. Min Act: -0.1700
Data Index: 1246376 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.8083. Min Act: -0.1700
Data Index: 396211 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.7458. Min Act: -0.1700
Data Index: 3539788 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.7458. Min Act: -0.1700
Data Index: 6859056 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 3465028 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 731376 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 397798 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 512905 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 3998022 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 3896397 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6833. Min Act: -0.1700
Data Index: 2210243 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0583. Min Range: -8.0583
Max Act: 7.6208. Min Act: -0.1700
Data Index: 458544 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19