Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0724. Min Range: -7.0724
Max Act: 7.0724. Min Act: -0.1700
Data Index: 6888144 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.8224. Min Act: -0.1700
Data Index: 2143185 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.8224. Min Act: -0.1700
Data Index: 6306166 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.7599. Min Act: -0.1700
Data Index: 6622968 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6974. Min Act: -0.1700
Data Index: 8190708 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6974. Min Act: -0.1700
Data Index: 4805312 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6349. Min Act: -0.1700
Data Index: 1494747 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6661. Min Act: -0.1700
Data Index: 8088136 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6036. Min Act: -0.1700
Data Index: 606327 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6036. Min Act: -0.1700
Data Index: 6080377 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.6036. Min Act: -0.1700
Data Index: 6326635 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5724. Min Act: -0.1700
Data Index: 1463499 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8269858 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5724. Min Act: -0.1700
Data Index: 7749519 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5411. Min Act: -0.1700
Data Index: 6503569 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5724. Min Act: -0.1700
Data Index: 418907 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5411. Min Act: -0.1700
Data Index: 5429039 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.5099. Min Act: -0.1700
Data Index: 8662600 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.4786. Min Act: -0.1700
Data Index: 1856337 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0724. Min Range: -7.0724
Max Act: 6.4786. Min Act: -0.1700
Data Index: 1538774 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19