Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 290 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.4528. Min Act: -0.1700
Data Index: 2655669 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.1715. Min Act: -0.1700
Data Index: 5871161 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.2028. Min Act: -0.1700
Data Index: 1384962 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.1715. Min Act: -0.1700
Data Index: 2346703 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.1403. Min Act: -0.1700
Data Index: 8333474 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.1090. Min Act: -0.1700
Data Index: 5764386 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.0778. Min Act: -0.1700
Data Index: 1933749 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.0465. Min Act: -0.1700
Data Index: 2242216 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4528. Min Range: -7.4528
Max Act: 7.0153. Min Act: -0.1700
Data Index: 4566764 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.9840. Min Act: -0.1700
Data Index: 6547859 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.9528. Min Act: -0.1700
Data Index: 814524 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8590. Min Act: -0.1700
Data Index: 8724105 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8590. Min Act: -0.1700
Data Index: 5710851 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8590. Min Act: -0.1700
Data Index: 6756371 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8278. Min Act: -0.1700
Data Index: 4318489 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8278. Min Act: -0.1700
Data Index: 7791135 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8278. Min Act: -0.1700
Data Index: 8400928 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.8278. Min Act: -0.1700
Data Index: 5111797 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.7965. Min Act: -0.1700
Data Index: 646019 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4528. Min Range: -7.4528
Max Act: 6.7965. Min Act: -0.1700
Data Index: 6122890 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19