Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5836 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1273. Min Range: -9.1273
Max Act: 9.1273. Min Act: -0.1700
Data Index: 1279270 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.6898. Min Act: -0.1700
Data Index: 7004009 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.5648. Min Act: -0.1700
Data Index: 7188757 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.5023. Min Act: -0.1700
Data Index: 6179411 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.4398. Min Act: -0.1700
Data Index: 8251895 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.1898. Min Act: -0.1700
Data Index: 597452 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.1898. Min Act: -0.1700
Data Index: 7301641 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.1273. Min Act: -0.1700
Data Index: 5858917 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.0648. Min Act: -0.1700
Data Index: 3641814 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.0648. Min Act: -0.1700
Data Index: 3582610 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1273. Min Range: -9.1273
Max Act: 8.0336. Min Act: -0.1700
Data Index: 863287 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9711. Min Act: -0.1700
Data Index: 5660328 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9398. Min Act: -0.1700
Data Index: 8323490 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9398. Min Act: -0.1700
Data Index: 3060052 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9398. Min Act: -0.1700
Data Index: 7404381 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9398. Min Act: -0.1700
Data Index: 8803849 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9711. Min Act: -0.1700
Data Index: 3880036 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.8773. Min Act: -0.1700
Data Index: 2174575 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9398. Min Act: -0.1700
Data Index: 4553735 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1273. Min Range: -9.1273
Max Act: 7.9398. Min Act: -0.1700
Data Index: 5901741 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19