Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1877. Min Range: -7.1877
Max Act: 7.1877. Min Act: -0.1700
Data Index: 3814822 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.8752. Min Act: -0.1700
Data Index: 4287138 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.8439. Min Act: -0.1700
Data Index: 6310263 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.8127. Min Act: -0.1700
Data Index: 7218179 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.8127. Min Act: -0.1700
Data Index: 6998510 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.8127. Min Act: -0.1700
Data Index: 575977 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.8439. Min Act: -0.1700
Data Index: 7671254 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.7502. Min Act: -0.1700
Data Index: 7554150 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.7189. Min Act: -0.1700
Data Index: 6117266 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.7502. Min Act: -0.1700
Data Index: 1416872 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.6564. Min Act: -0.1700
Data Index: 6177550 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.6252. Min Act: -0.1700
Data Index: 7190140 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.6252. Min Act: -0.1700
Data Index: 4187675 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5627. Min Act: -0.1700
Data Index: 7836384 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5939. Min Act: -0.1700
Data Index: 4632730 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5627. Min Act: -0.1700
Data Index: 1611956 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5627. Min Act: -0.1700
Data Index: 3422325 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5314. Min Act: -0.1700
Data Index: 3324181 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5314. Min Act: -0.1700
Data Index: 6855315 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1877. Min Range: -7.1877
Max Act: 6.5002. Min Act: -0.1700
Data Index: 6126630 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19