Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2106. Min Range: -7.2106
Max Act: 7.2106. Min Act: -0.1700
Data Index: 8110623 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2106. Min Range: -7.2106
Max Act: 7.0544. Min Act: -0.1700
Data Index: 8405854 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2106. Min Range: -7.2106
Max Act: 7.0231. Min Act: -0.1700
Data Index: 2796277 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2106. Min Range: -7.2106
Max Act: 7.0231. Min Act: -0.1700
Data Index: 4608671 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.9919. Min Act: -0.1700
Data Index: 5369957 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.9606. Min Act: -0.1700
Data Index: 5220902 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.7731. Min Act: -0.1700
Data Index: 5635180 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.8044. Min Act: -0.1700
Data Index: 4073438 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.7731. Min Act: -0.1700
Data Index: 7384135 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.6794. Min Act: -0.1700
Data Index: 2633580 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.6794. Min Act: -0.1700
Data Index: 7726908 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.6481. Min Act: -0.1700
Data Index: 5294941 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.6169. Min Act: -0.1700
Data Index: 3581264 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.6169. Min Act: -0.1700
Data Index: 4696607 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.6169. Min Act: -0.1700
Data Index: 3479490 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.5856. Min Act: -0.1700
Data Index: 1994445 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.5856. Min Act: -0.1700
Data Index: 6887827 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.5856. Min Act: -0.1700
Data Index: 515737 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.5856. Min Act: -0.1700
Data Index: 1987562 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2106. Min Range: -7.2106
Max Act: 6.5544. Min Act: -0.1700
Data Index: 3962976 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19