Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.5217. Min Act: -0.1700
Data Index: 1221441 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.4905. Min Act: -0.1700
Data Index: 3780924 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.3030. Min Act: -0.1700
Data Index: 2815706 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.3030. Min Act: -0.1700
Data Index: 8519340 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.3342. Min Act: -0.1700
Data Index: 6138069 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.3030. Min Act: -0.1700
Data Index: 3424302 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.2717. Min Act: -0.1700
Data Index: 4361965 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.2405. Min Act: -0.1700
Data Index: 123134 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.2405. Min Act: -0.1700
Data Index: 8267562 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.2405. Min Act: -0.1700
Data Index: 3158446 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.2405. Min Act: -0.1700
Data Index: 5409265 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.2092. Min Act: -0.1700
Data Index: 3189797 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1780. Min Act: -0.1700
Data Index: 589429 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1780. Min Act: -0.1700
Data Index: 3382147 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1780. Min Act: -0.1700
Data Index: 6517404 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1780. Min Act: -0.1700
Data Index: 1787690 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1467. Min Act: -0.1700
Data Index: 6838254 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1155. Min Act: -0.1700
Data Index: 8056682 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1467. Min Act: -0.1700
Data Index: 2999888 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5217. Min Range: -6.5217
Max Act: 6.1155. Min Act: -0.1700
Data Index: 3657591 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19