Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2076. Min Range: -5.2076
Max Act: 5.2076. Min Act: -0.1700
Data Index: 5763754 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2076. Min Range: -5.2076
Max Act: 5.0514. Min Act: -0.1700
Data Index: 1752003 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.9576. Min Act: -0.1700
Data Index: 4366485 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2076. Min Range: -5.2076
Max Act: 5.0201. Min Act: -0.1700
Data Index: 1841446 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2076. Min Range: -5.2076
Max Act: 5.0201. Min Act: -0.1700
Data Index: 6415700 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.9576. Min Act: -0.1700
Data Index: 7307047 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.9889. Min Act: -0.1700
Data Index: 5806295 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.9576. Min Act: -0.1700
Data Index: 8141417 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8951. Min Act: -0.1700
Data Index: 4802482 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8639. Min Act: -0.1700
Data Index: 7951474 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8951. Min Act: -0.1700
Data Index: 5722387 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8639. Min Act: -0.1700
Data Index: 5601747 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8951. Min Act: -0.1700
Data Index: 4536114 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8639. Min Act: -0.1700
Data Index: 1172776 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8014. Min Act: -0.1700
Data Index: 4076932 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8326. Min Act: -0.1700
Data Index: 4919001 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8326. Min Act: -0.1700
Data Index: 5996529 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8326. Min Act: -0.1700
Data Index: 6037107 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8326. Min Act: -0.1700
Data Index: 4411913 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2076. Min Range: -5.2076
Max Act: 4.8014. Min Act: -0.1700
Data Index: 3818683 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19