Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1046 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1642. Min Range: -5.1642
Max Act: 5.1642. Min Act: -0.1700
Data Index: 265516 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1642. Min Range: -5.1642
Max Act: 5.1017. Min Act: -0.1700
Data Index: 2492251 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1642. Min Range: -5.1642
Max Act: 5.0392. Min Act: -0.1700
Data Index: 4896125 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1642. Min Range: -5.1642
Max Act: 5.0392. Min Act: -0.1700
Data Index: 5465124 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1642. Min Range: -5.1642
Max Act: 5.0080. Min Act: -0.1700
Data Index: 1800013 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9767. Min Act: -0.1700
Data Index: 612996 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9767. Min Act: -0.1700
Data Index: 2640147 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9455. Min Act: -0.1700
Data Index: 5602034 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9142. Min Act: -0.1700
Data Index: 2955493 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9142. Min Act: -0.1700
Data Index: 6110467 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9142. Min Act: -0.1700
Data Index: 2188188 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8830. Min Act: -0.1700
Data Index: 3712247 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9142. Min Act: -0.1700
Data Index: 6573725 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.9142. Min Act: -0.1700
Data Index: 6216553 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8830. Min Act: -0.1700
Data Index: 282126 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8830. Min Act: -0.1700
Data Index: 55384 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8830. Min Act: -0.1700
Data Index: 2761647 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8830. Min Act: -0.1700
Data Index: 6945839 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8517. Min Act: -0.1700
Data Index: 4452875 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1642. Min Range: -5.1642
Max Act: 4.8205. Min Act: -0.1700
Data Index: 4937717 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19