Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5371 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.7512. Min Act: -0.1700
Data Index: 468656 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.7512. Min Act: -0.1700
Data Index: 8049176 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.6887. Min Act: -0.1700
Data Index: 8648090 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.4387. Min Act: -0.1700
Data Index: 986500 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.4387. Min Act: -0.1700
Data Index: 7149279 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.3762. Min Act: -0.1700
Data Index: 1432749 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.3137. Min Act: -0.1700
Data Index: 3482131 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.3762. Min Act: -0.1700
Data Index: 8701772 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.3762. Min Act: -0.1700
Data Index: 3551810 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.3137. Min Act: -0.1700
Data Index: 1309169 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 417841 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 315732 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 7943845 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 8088070 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 5914365 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 4625460 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.1262. Min Act: -0.1700
Data Index: 1883485 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.1262. Min Act: -0.1700
Data Index: 783184 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.1262. Min Act: -0.1700
Data Index: 5830516 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7512. Min Range: -8.7512
Max Act: 8.0637. Min Act: -0.1700
Data Index: 7817347 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19