Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.3756. Min Act: -0.1700
Data Index: 1517842 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.3131. Min Act: -0.1700
Data Index: 6011675 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.1881. Min Act: -0.1700
Data Index: 4023965 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2839685 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.1568. Min Act: -0.1700
Data Index: 6855229 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.1568. Min Act: -0.1700
Data Index: 5712098 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3756. Min Range: -6.3756
Max Act: 6.0631. Min Act: -0.1700
Data Index: 848256 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.9693. Min Act: -0.1700
Data Index: 3898380 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.9693. Min Act: -0.1700
Data Index: 7271820 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.9693. Min Act: -0.1700
Data Index: 4615962 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8756. Min Act: -0.1700
Data Index: 2096524 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8756. Min Act: -0.1700
Data Index: 5237931 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4620321 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8443. Min Act: -0.1700
Data Index: 7236872 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4071472 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8131. Min Act: -0.1700
Data Index: 1365205 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8131. Min Act: -0.1700
Data Index: 8155020 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.8443. Min Act: -0.1700
Data Index: 85061 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.7818. Min Act: -0.1700
Data Index: 6989299 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3756. Min Range: -6.3756
Max Act: 5.7818. Min Act: -0.1700
Data Index: 6183526 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19