Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9806. Min Act: -0.1700
Data Index: 392513 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9633. Min Act: -0.1700
Data Index: 807571 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9460. Min Act: -0.1700
Data Index: 6415442 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9460. Min Act: -0.1700
Data Index: 4094138 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9374. Min Act: -0.1700
Data Index: 7954919 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9202. Min Act: -0.1700
Data Index: 5280283 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9202. Min Act: -0.1700
Data Index: 120879 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9031. Min Act: -0.1700
Data Index: 1028308 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.9031. Min Act: -0.1700
Data Index: 6423881 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8945. Min Act: -0.1700
Data Index: 2034531 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8945. Min Act: -0.1700
Data Index: 2363370 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8860. Min Act: -0.1699
Data Index: 8223063 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8860. Min Act: -0.1700
Data Index: 906355 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8945. Min Act: -0.1700
Data Index: 2584231 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8860. Min Act: -0.1700
Data Index: 2851461 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8775. Min Act: -0.1700
Data Index: 2581764 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8605. Min Act: -0.1700
Data Index: 385606 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8690. Min Act: -0.1700
Data Index: 1443244 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8605. Min Act: -0.1700
Data Index: 1870952 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9806. Min Range: -0.9806
Max Act: 0.8520. Min Act: -0.1700
Data Index: 4219333 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19