Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.8400. Min Act: -0.1700
Data Index: 3446155 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.6525. Min Act: -0.1700
Data Index: 1510724 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.5588. Min Act: -0.1700
Data Index: 7070262 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.5275. Min Act: -0.1700
Data Index: 5989393 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.4963. Min Act: -0.1700
Data Index: 5154578 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.4338. Min Act: -0.1700
Data Index: 5398293 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3713. Min Act: -0.1700
Data Index: 5551634 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3400. Min Act: -0.1700
Data Index: 3378771 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3713. Min Act: -0.1700
Data Index: 4124411 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3400. Min Act: -0.1700
Data Index: 3887416 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3088. Min Act: -0.1700
Data Index: 8132478 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3088. Min Act: -0.1700
Data Index: 4805953 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.3088. Min Act: -0.1700
Data Index: 5408107 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2775. Min Act: -0.1700
Data Index: 4363477 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2463. Min Act: -0.1700
Data Index: 6804601 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2463. Min Act: -0.1700
Data Index: 2740375 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2463. Min Act: -0.1700
Data Index: 5243508 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2150. Min Act: -0.1700
Data Index: 93269 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2150. Min Act: -0.1700
Data Index: 1289623 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8400. Min Range: -6.8400
Max Act: 6.2150. Min Act: -0.1700
Data Index: 3496732 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19