Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.3889. Min Act: -0.1700
Data Index: 5360129 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.2639. Min Act: -0.1700
Data Index: 1468647 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.1389. Min Act: -0.1700
Data Index: 8435019 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.0139. Min Act: -0.1700
Data Index: 5240268 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.0139. Min Act: -0.1700
Data Index: 1043530 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.0139. Min Act: -0.1700
Data Index: 4979533 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3889. Min Range: -9.3889
Max Act: 9.0139. Min Act: -0.1700
Data Index: 3173054 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.9514. Min Act: -0.1700
Data Index: 6986296 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.9514. Min Act: -0.1700
Data Index: 5618176 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 7878686 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 6969733 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 755381 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 4032335 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 2110038 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8264. Min Act: -0.1700
Data Index: 567963 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 4894044 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8889. Min Act: -0.1700
Data Index: 8279971 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.8264. Min Act: -0.1700
Data Index: 974148 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.7639. Min Act: -0.1700
Data Index: 2784453 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3889. Min Range: -9.3889
Max Act: 8.7639. Min Act: -0.1700
Data Index: 6045239 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19