Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4007 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.4561. Min Act: -0.1700
Data Index: 3264792 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.2686. Min Act: -0.1700
Data Index: 2910221 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.2061. Min Act: -0.1700
Data Index: 3411788 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.1749. Min Act: -0.1700
Data Index: 4197990 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.0811. Min Act: -0.1700
Data Index: 7463715 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.0499. Min Act: -0.1700
Data Index: 3756079 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4561. Min Range: -5.4561
Max Act: 5.0186. Min Act: -0.1700
Data Index: 6583134 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.9874. Min Act: -0.1700
Data Index: 958412 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.9561. Min Act: -0.1700
Data Index: 6578486 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.9561. Min Act: -0.1700
Data Index: 3627205 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.9249. Min Act: -0.1700
Data Index: 5363889 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.9249. Min Act: -0.1700
Data Index: 2365010 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.9249. Min Act: -0.1700
Data Index: 1393100 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.8624. Min Act: -0.1700
Data Index: 3021827 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.8624. Min Act: -0.1700
Data Index: 6767773 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.8311. Min Act: -0.1700
Data Index: 4983887 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.8311. Min Act: -0.1700
Data Index: 5450511 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.7999. Min Act: -0.1700
Data Index: 3387823 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.8624. Min Act: -0.1700
Data Index: 6527302 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4561. Min Range: -5.4561
Max Act: 4.8311. Min Act: -0.1700
Data Index: 4215307 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19