Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1002. Min Range: -8.1002
Max Act: 8.1002. Min Act: -0.1700
Data Index: 7053754 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.9752. Min Act: -0.1700
Data Index: 6455407 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.9752. Min Act: -0.1700
Data Index: 2395363 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.9439. Min Act: -0.1700
Data Index: 7340256 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.8502. Min Act: -0.1700
Data Index: 3657546 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.8189. Min Act: -0.1700
Data Index: 698471 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.8189. Min Act: -0.1700
Data Index: 7122600 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.7877. Min Act: -0.1700
Data Index: 4395934 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.7877. Min Act: -0.1700
Data Index: 6326507 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.7252. Min Act: -0.1700
Data Index: 4655172 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.7564. Min Act: -0.1700
Data Index: 4818668 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.7252. Min Act: -0.1700
Data Index: 344513 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6939. Min Act: -0.1700
Data Index: 260846 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6627. Min Act: -0.1700
Data Index: 2329119 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6314. Min Act: -0.1700
Data Index: 171762 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6627. Min Act: -0.1700
Data Index: 4845722 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6314. Min Act: -0.1700
Data Index: 1686832 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6627. Min Act: -0.1700
Data Index: 4304817 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6314. Min Act: -0.1700
Data Index: 6132534 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1002. Min Range: -8.1002
Max Act: 7.6314. Min Act: -0.1700
Data Index: 4137904 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19