Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6004 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.5609. Min Act: -0.1700
Data Index: 5823877 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.2796. Min Act: -0.1700
Data Index: 1475850 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.2171. Min Act: -0.1700
Data Index: 1139640 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.2484. Min Act: -0.1700
Data Index: 1509629 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.1546. Min Act: -0.1700
Data Index: 7707899 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.1546. Min Act: -0.1700
Data Index: 3651952 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.1234. Min Act: -0.1700
Data Index: 2321766 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.0921. Min Act: -0.1700
Data Index: 7564003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.0921. Min Act: -0.1700
Data Index: 1592167 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.0921. Min Act: -0.1700
Data Index: 2325415 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5609. Min Range: -7.5609
Max Act: 7.0296. Min Act: -0.1700
Data Index: 8318094 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9984. Min Act: -0.1700
Data Index: 8557093 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9671. Min Act: -0.1700
Data Index: 3982334 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9671. Min Act: -0.1700
Data Index: 4587559 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9046. Min Act: -0.1700
Data Index: 3654016 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9359. Min Act: -0.1700
Data Index: 8175143 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9046. Min Act: -0.1700
Data Index: 7509899 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9046. Min Act: -0.1700
Data Index: 6598985 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.9046. Min Act: -0.1700
Data Index: 8579192 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5609. Min Range: -7.5609
Max Act: 6.8734. Min Act: -0.1700
Data Index: 2252983 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19