Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.6690. Min Act: -0.1700
Data Index: 2109524 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.4502. Min Act: -0.1700
Data Index: 6549671 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.2627. Min Act: -0.1700
Data Index: 6587325 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2332825 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.2002. Min Act: -0.1700
Data Index: 6587311 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.2002. Min Act: -0.1700
Data Index: 6587322 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.2002. Min Act: -0.1700
Data Index: 6149732 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.2002. Min Act: -0.1700
Data Index: 4137463 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.1690. Min Act: -0.1700
Data Index: 885748 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.1690. Min Act: -0.1700
Data Index: 7881691 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.1065. Min Act: -0.1700
Data Index: 6993759 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.1377. Min Act: -0.1700
Data Index: 7504588 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.1065. Min Act: -0.1700
Data Index: 2054719 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0752. Min Act: -0.1700
Data Index: 5935195 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0440. Min Act: -0.1700
Data Index: 86877 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0440. Min Act: -0.1700
Data Index: 1701737 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0440. Min Act: -0.1700
Data Index: 7470910 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0127. Min Act: -0.1700
Data Index: 7785083 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0440. Min Act: -0.1700
Data Index: 5378848 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6690. Min Range: -7.6690
Max Act: 7.0752. Min Act: -0.1700
Data Index: 8287027 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19