Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4507 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1294. Min Range: -5.1294
Max Act: 5.1294. Min Act: -0.1700
Data Index: 7357093 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1294. Min Range: -5.1294
Max Act: 5.0669. Min Act: -0.1700
Data Index: 2861821 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9732. Min Act: -0.1700
Data Index: 2118930 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9732. Min Act: -0.1700
Data Index: 5439329 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9732. Min Act: -0.1700
Data Index: 3584315 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9419. Min Act: -0.1700
Data Index: 6195697 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9419. Min Act: -0.1700
Data Index: 4461385 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9107. Min Act: -0.1700
Data Index: 5589929 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9107. Min Act: -0.1700
Data Index: 851561 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.8794. Min Act: -0.1700
Data Index: 5242965 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.8794. Min Act: -0.1700
Data Index: 975191 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.9107. Min Act: -0.1700
Data Index: 1786386 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.8482. Min Act: -0.1700
Data Index: 4088088 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.8169. Min Act: -0.1700
Data Index: 6543819 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.8169. Min Act: -0.1700
Data Index: 1301625 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.7857. Min Act: -0.1700
Data Index: 2951954 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.7544. Min Act: -0.1700
Data Index: 2672394 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.7544. Min Act: -0.1700
Data Index: 1494286 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.7544. Min Act: -0.1700
Data Index: 5913520 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1294. Min Range: -5.1294
Max Act: 4.7544. Min Act: -0.1700
Data Index: 4096210 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19