Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.4368. Min Act: -0.1700
Data Index: 4560085 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.3741. Min Act: -0.1700
Data Index: 7470549 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.3741. Min Act: -0.1700
Data Index: 3841733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.3584. Min Act: -0.1700
Data Index: 29898 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.3427. Min Act: -0.1700
Data Index: 2915527 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.3113. Min Act: -0.1700
Data Index: 3912410 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.3113. Min Act: -0.1700
Data Index: 7055520 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2956. Min Act: -0.1700
Data Index: 768002 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2799. Min Act: -0.1700
Data Index: 2798039 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2642. Min Act: -0.1700
Data Index: 1730650 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2171. Min Act: -0.1700
Data Index: 917826 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2328. Min Act: -0.1700
Data Index: 694838 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2171. Min Act: -0.1700
Data Index: 7260597 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2171. Min Act: -0.1700
Data Index: 426122 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2328. Min Act: -0.1700
Data Index: 2803621 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2171. Min Act: -0.1700
Data Index: 6973012 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.1856. Min Act: -0.1700
Data Index: 4113812 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.2014. Min Act: -0.1700
Data Index: 3141555 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.1699. Min Act: -0.1700
Data Index: 7076754 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4368. Min Range: -3.4368
Max Act: 3.1542. Min Act: -0.1700
Data Index: 4581704 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19