Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.8612. Min Act: -0.1700
Data Index: 2162231 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.8299. Min Act: -0.1700
Data Index: 8827165 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.8299. Min Act: -0.1700
Data Index: 2563209 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.7674. Min Act: -0.1700
Data Index: 6516855 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.7362. Min Act: -0.1700
Data Index: 3695500 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.7362. Min Act: -0.1700
Data Index: 939924 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.7049. Min Act: -0.1700
Data Index: 4018311 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6737. Min Act: -0.1700
Data Index: 8339444 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.7049. Min Act: -0.1700
Data Index: 5113783 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6737. Min Act: -0.1700
Data Index: 4532454 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.7049. Min Act: -0.1700
Data Index: 2701153 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6737. Min Act: -0.1700
Data Index: 4018326 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 784068 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6424. Min Act: -0.1700
Data Index: 4712309 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 7752490 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 7942383 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 1979429 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 1374367 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 4890662 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8612. Min Range: -6.8612
Max Act: 6.6112. Min Act: -0.1700
Data Index: 7108819 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19