Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.1960. Min Act: -0.1700
Data Index: 2935863 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.1488. Min Act: -0.1700
Data Index: 8318893 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.0858. Min Act: -0.1700
Data Index: 7249767 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.0858. Min Act: -0.1700
Data Index: 2401525 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.0385. Min Act: -0.1700
Data Index: 1698413 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.0069. Min Act: -0.1700
Data Index: 6365924 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1960. Min Range: -3.1960
Max Act: 3.0069. Min Act: -0.1700
Data Index: 8573807 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9753. Min Act: -0.1700
Data Index: 7863090 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9753. Min Act: -0.1700
Data Index: 7870267 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9595. Min Act: -0.1700
Data Index: 3084309 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9436. Min Act: -0.1700
Data Index: 5034527 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9595. Min Act: -0.1700
Data Index: 4005518 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9595. Min Act: -0.1700
Data Index: 2008303 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9278. Min Act: -0.1700
Data Index: 7745405 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9278. Min Act: -0.1700
Data Index: 6859936 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9278. Min Act: -0.1700
Data Index: 6371392 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9436. Min Act: -0.1700
Data Index: 5598027 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9436. Min Act: -0.1700
Data Index: 4175069 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9278. Min Act: -0.1700
Data Index: 6918278 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1960. Min Range: -3.1960
Max Act: 2.9278. Min Act: -0.1700
Data Index: 4191790 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19