Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.5724. Min Act: -0.1700
Data Index: 3173757 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.3224. Min Act: -0.1700
Data Index: 347720 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.1974. Min Act: -0.1700
Data Index: 3565670 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.1974. Min Act: -0.1700
Data Index: 5911985 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.0099. Min Act: -0.1700
Data Index: 8608338 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.0724. Min Act: -0.1700
Data Index: 1480152 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.0099. Min Act: -0.1700
Data Index: 2562588 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.9474. Min Act: -0.1700
Data Index: 2051707 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.9474. Min Act: -0.1700
Data Index: 7935665 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5724. Min Range: -9.5724
Max Act: 9.0099. Min Act: -0.1700
Data Index: 963394 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.9474. Min Act: -0.1700
Data Index: 2051709 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.9474. Min Act: -0.1700
Data Index: 3641999 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8849. Min Act: -0.1700
Data Index: 7384648 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8849. Min Act: -0.1700
Data Index: 6072313 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8849. Min Act: -0.1700
Data Index: 2425207 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8224. Min Act: -0.1700
Data Index: 6813711 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8224. Min Act: -0.1700
Data Index: 3475695 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8224. Min Act: -0.1700
Data Index: 5122679 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8224. Min Act: -0.1700
Data Index: 6916164 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5724. Min Range: -9.5724
Max Act: 8.8224. Min Act: -0.1700
Data Index: 5365788 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19