Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1537. Min Range: -6.1537
Max Act: 6.1537. Min Act: -0.1700
Data Index: 762389 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1537. Min Range: -6.1537
Max Act: 6.0599. Min Act: -0.1700
Data Index: 6834511 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1537. Min Range: -6.1537
Max Act: 6.0599. Min Act: -0.1700
Data Index: 4701334 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1537. Min Range: -6.1537
Max Act: 6.0287. Min Act: -0.1700
Data Index: 1531658 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1537. Min Range: -6.1537
Max Act: 6.0287. Min Act: -0.1700
Data Index: 6316532 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1537. Min Range: -6.1537
Max Act: 6.0287. Min Act: -0.1700
Data Index: 2409463 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9974. Min Act: -0.1700
Data Index: 8171842 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9974. Min Act: -0.1700
Data Index: 4366196 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9349. Min Act: -0.1700
Data Index: 5964654 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9349. Min Act: -0.1700
Data Index: 6209390 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9349. Min Act: -0.1700
Data Index: 8392075 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9037. Min Act: -0.1700
Data Index: 8087310 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.8724. Min Act: -0.1700
Data Index: 3927993 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9037. Min Act: -0.1700
Data Index: 8236343 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.9037. Min Act: -0.1700
Data Index: 6760184 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.8724. Min Act: -0.1700
Data Index: 4627385 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.8724. Min Act: -0.1700
Data Index: 2588069 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.8412. Min Act: -0.1700
Data Index: 4809894 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.8724. Min Act: -0.1700
Data Index: 2971532 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1537. Min Range: -6.1537
Max Act: 5.8724. Min Act: -0.1700
Data Index: 5017971 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19