Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3702 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6318. Min Range: -6.6318
Max Act: 6.6318. Min Act: -0.1700
Data Index: 2767135 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6318. Min Range: -6.6318
Max Act: 6.0693. Min Act: -0.1700
Data Index: 1017423 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.7880. Min Act: -0.1700
Data Index: 7393161 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6943. Min Act: -0.1700
Data Index: 5719201 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6943. Min Act: -0.1700
Data Index: 7533554 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6630. Min Act: -0.1700
Data Index: 5636284 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6943. Min Act: -0.1700
Data Index: 180384 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6630. Min Act: -0.1700
Data Index: 2677534 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6318. Min Act: -0.1700
Data Index: 6198735 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6005. Min Act: -0.1700
Data Index: 3316562 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.6318. Min Act: -0.1700
Data Index: 3927702 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.5068. Min Act: -0.1700
Data Index: 1950036 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.5068. Min Act: -0.1700
Data Index: 3026286 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.5068. Min Act: -0.1700
Data Index: 1388708 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.4755. Min Act: -0.1700
Data Index: 8486427 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.4755. Min Act: -0.1700
Data Index: 6614819 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.4755. Min Act: -0.1700
Data Index: 6397376 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.4443. Min Act: -0.1700
Data Index: 4744683 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.4443. Min Act: -0.1700
Data Index: 8131859 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6318. Min Range: -6.6318
Max Act: 5.4443. Min Act: -0.1700
Data Index: 7393162 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19