Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5370 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3610. Min Range: -7.3610
Max Act: 7.3610. Min Act: -0.1700
Data Index: 6474659 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3610. Min Range: -7.3610
Max Act: 7.0172. Min Act: -0.1700
Data Index: 6127090 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.9547. Min Act: -0.1700
Data Index: 7624625 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.8922. Min Act: -0.1700
Data Index: 8786794 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.8297. Min Act: -0.1700
Data Index: 8390548 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.8610. Min Act: -0.1700
Data Index: 4827786 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.8297. Min Act: -0.1700
Data Index: 4866229 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.7985. Min Act: -0.1700
Data Index: 4607930 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.7672. Min Act: -0.1700
Data Index: 5962744 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6735. Min Act: -0.1700
Data Index: 5630740 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.7047. Min Act: -0.1700
Data Index: 6835372 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6735. Min Act: -0.1700
Data Index: 5740451 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6735. Min Act: -0.1700
Data Index: 5998453 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6422. Min Act: -0.1700
Data Index: 6702592 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6422. Min Act: -0.1700
Data Index: 2736926 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6422. Min Act: -0.1700
Data Index: 8170449 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6110. Min Act: -0.1700
Data Index: 8522252 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6110. Min Act: -0.1700
Data Index: 5020902 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.6110. Min Act: -0.1700
Data Index: 3892885 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3610. Min Range: -7.3610
Max Act: 6.5797. Min Act: -0.1700
Data Index: 7020162 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19