Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4308 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1812. Min Range: -5.1812
Max Act: 5.1812. Min Act: -0.1700
Data Index: 6611013 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1812. Min Range: -5.1812
Max Act: 5.0875. Min Act: -0.1700
Data Index: 8004380 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9937. Min Act: -0.1700
Data Index: 3040547 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9937. Min Act: -0.1700
Data Index: 8541510 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9312. Min Act: -0.1700
Data Index: 278615 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9312. Min Act: -0.1700
Data Index: 1745481 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9000. Min Act: -0.1700
Data Index: 8169506 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.9000. Min Act: -0.1700
Data Index: 1364376 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8687. Min Act: -0.1700
Data Index: 7102730 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8687. Min Act: -0.1700
Data Index: 6856125 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8687. Min Act: -0.1700
Data Index: 8801846 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 4996961 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 3169429 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.8062. Min Act: -0.1700
Data Index: 3429688 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7750. Min Act: -0.1700
Data Index: 5786763 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7750. Min Act: -0.1700
Data Index: 4548115 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7750. Min Act: -0.1700
Data Index: 700286 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7750. Min Act: -0.1700
Data Index: 3325096 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7750. Min Act: -0.1700
Data Index: 7558482 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1812. Min Range: -5.1812
Max Act: 4.7437. Min Act: -0.1700
Data Index: 1906213 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19