Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4256. Min Range: -6.4256
Max Act: 6.4256. Min Act: -0.1700
Data Index: 4874571 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4256. Min Range: -6.4256
Max Act: 6.2068. Min Act: -0.1700
Data Index: 5976914 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4256. Min Range: -6.4256
Max Act: 6.1756. Min Act: -0.1700
Data Index: 993641 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4256. Min Range: -6.4256
Max Act: 6.1443. Min Act: -0.1700
Data Index: 8377403 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.9568. Min Act: -0.1700
Data Index: 6251561 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7065436 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.9256. Min Act: -0.1700
Data Index: 3268388 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.9568. Min Act: -0.1700
Data Index: 4394207 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.9256. Min Act: -0.1700
Data Index: 7476614 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8943. Min Act: -0.1700
Data Index: 3759077 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8631. Min Act: -0.1700
Data Index: 3927857 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1063688 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8318. Min Act: -0.1700
Data Index: 964616 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8318. Min Act: -0.1700
Data Index: 3483288 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8318. Min Act: -0.1700
Data Index: 1665043 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8318. Min Act: -0.1700
Data Index: 829660 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8318. Min Act: -0.1700
Data Index: 1495571 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8006. Min Act: -0.1700
Data Index: 8101986 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.8006. Min Act: -0.1700
Data Index: 5703242 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4256. Min Range: -6.4256
Max Act: 5.7693. Min Act: -0.1700
Data Index: 5216342 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19