Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5034 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1482. Min Range: -8.1482
Max Act: 8.1482. Min Act: -0.1700
Data Index: 4630173 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1482. Min Range: -8.1482
Max Act: 8.1482. Min Act: -0.1700
Data Index: 6013429 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1482. Min Range: -8.1482
Max Act: 8.0857. Min Act: -0.1700
Data Index: 2634011 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1482. Min Range: -8.1482
Max Act: 8.0857. Min Act: -0.1700
Data Index: 134027 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1482. Min Range: -8.1482
Max Act: 8.0232. Min Act: -0.1700
Data Index: 1887368 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1482. Min Range: -8.1482
Max Act: 8.0232. Min Act: -0.1700
Data Index: 3375811 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.9607. Min Act: -0.1700
Data Index: 5579874 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.8982. Min Act: -0.1700
Data Index: 378905 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.8357. Min Act: -0.1700
Data Index: 5705161 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.8357. Min Act: -0.1700
Data Index: 5822351 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.8357. Min Act: -0.1700
Data Index: 5077010 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.7732. Min Act: -0.1700
Data Index: 6300363 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.7732. Min Act: -0.1700
Data Index: 1054904 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.7107. Min Act: -0.1700
Data Index: 7997999 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 3785796 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 7384001 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 889079 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 1406362 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 1061218 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1482. Min Range: -8.1482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 2042277 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19