Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2744. Min Act: -0.1700
Data Index: 3056819 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2432. Min Act: -0.1700
Data Index: 7722345 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2119. Min Act: -0.1700
Data Index: 1906248 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2119. Min Act: -0.1700
Data Index: 7495610 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2119. Min Act: -0.1700
Data Index: 1897384 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2119. Min Act: -0.1700
Data Index: 6801880 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.2432. Min Act: -0.1700
Data Index: 2029067 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.1182. Min Act: -0.1700
Data Index: 1014014 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.1182. Min Act: -0.1700
Data Index: 6541678 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.1182. Min Act: -0.1700
Data Index: 5288670 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.1182. Min Act: -0.1700
Data Index: 8126802 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.1182. Min Act: -0.1700
Data Index: 8028280 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0869. Min Act: -0.1700
Data Index: 2648889 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0869. Min Act: -0.1700
Data Index: 1866306 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0557. Min Act: -0.1700
Data Index: 3888819 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0557. Min Act: -0.1700
Data Index: 5436899 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0557. Min Act: -0.1700
Data Index: 1107073 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0557. Min Act: -0.1700
Data Index: 5047146 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0869. Min Act: -0.1700
Data Index: 675544 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2744. Min Range: -4.2744
Max Act: 4.0244. Min Act: -0.1700
Data Index: 4951899 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19