Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.6877. Min Act: -0.1700
Data Index: 7812553 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.4377. Min Act: -0.1700
Data Index: 8469886 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.3752. Min Act: -0.1700
Data Index: 31953 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.4377. Min Act: -0.1700
Data Index: 4912489 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.2502. Min Act: -0.1700
Data Index: 3328305 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.2502. Min Act: -0.1700
Data Index: 2768508 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.2502. Min Act: -0.1700
Data Index: 33298 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.1877. Min Act: -0.1700
Data Index: 4188297 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.1564. Min Act: -0.1700
Data Index: 7460759 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 3805362 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 6999148 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 8700452 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 3228291 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0314. Min Act: -0.1700
Data Index: 7773796 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0314. Min Act: -0.1700
Data Index: 5713515 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 2137750 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 4364739 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0627. Min Act: -0.1700
Data Index: 4401678 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0314. Min Act: -0.1700
Data Index: 7119705 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6877. Min Range: -8.6877
Max Act: 8.0314. Min Act: -0.1700
Data Index: 6263165 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19