Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 519 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.1112. Min Range: -14.1112
Max Act: 14.1112. Min Act: -0.1700
Data Index: 5537852 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1112. Min Range: -14.1112
Max Act: 13.3612. Min Act: -0.1700
Data Index: 6320857 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.9862. Min Act: -0.1700
Data Index: 7487404 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1112. Min Range: -14.1112
Max Act: 13.0487. Min Act: -0.1700
Data Index: 4137032 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.9237. Min Act: -0.1700
Data Index: 487124 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.8612. Min Act: -0.1700
Data Index: 8182793 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.7362. Min Act: -0.1700
Data Index: 7619581 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.6112. Min Act: -0.1700
Data Index: 7062446 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.7362. Min Act: -0.1700
Data Index: 5407600 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.6112. Min Act: -0.1700
Data Index: 709229 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.6737. Min Act: -0.1700
Data Index: 6089771 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.6737. Min Act: -0.1700
Data Index: 8754064 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.4237. Min Act: -0.1700
Data Index: 8315766 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.4237. Min Act: -0.1700
Data Index: 5307070 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.0487. Min Act: -0.1700
Data Index: 8753999 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.4237. Min Act: -0.1700
Data Index: 4097119 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.7987. Min Act: -0.1700
Data Index: 5003598 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.4237. Min Act: -0.1700
Data Index: 6158091 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.4237. Min Act: -0.1700
Data Index: 5407598 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1112. Min Range: -14.1112
Max Act: 12.4862. Min Act: -0.1700
Data Index: 6365136 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19