Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5561. Min Range: -11.5561
Max Act: 11.5561. Min Act: -0.1700
Data Index: 8101598 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5561. Min Range: -11.5561
Max Act: 11.4311. Min Act: -0.1700
Data Index: 918295 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5561. Min Range: -11.5561
Max Act: 11.3061. Min Act: -0.1700
Data Index: 381968 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5561. Min Range: -11.5561
Max Act: 11.1811. Min Act: -0.1700
Data Index: 6571997 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.8061. Min Act: -0.1700
Data Index: 7365650 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.8061. Min Act: -0.1700
Data Index: 6281351 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.8061. Min Act: -0.1700
Data Index: 4864003 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.6811. Min Act: -0.1700
Data Index: 5829753 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.6811. Min Act: -0.1700
Data Index: 1113528 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.6186. Min Act: -0.1700
Data Index: 8052201 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.6186. Min Act: -0.1700
Data Index: 835341 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.6186. Min Act: -0.1700
Data Index: 6085845 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.5561. Min Act: -0.1700
Data Index: 1700914 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.5561. Min Act: -0.1700
Data Index: 6998044 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.4936. Min Act: -0.1700
Data Index: 2838551 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.4936. Min Act: -0.1700
Data Index: 6572519 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.4936. Min Act: -0.1700
Data Index: 1379141 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.4936. Min Act: -0.1700
Data Index: 1836690 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.4936. Min Act: -0.1700
Data Index: 3265058 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5561. Min Range: -11.5561
Max Act: 10.4311. Min Act: -0.1700
Data Index: 7002543 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19