Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4431 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.8994. Min Act: -0.1700
Data Index: 5540664 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.6494. Min Act: -0.1700
Data Index: 8059249 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.2744. Min Act: -0.1700
Data Index: 860594 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.2119. Min Act: -0.1700
Data Index: 7111025 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.2119. Min Act: -0.1700
Data Index: 2430425 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.2119. Min Act: -0.1700
Data Index: 6460869 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.1494. Min Act: -0.1700
Data Index: 7477440 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.2744. Min Act: -0.1700
Data Index: 436156 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0869. Min Act: -0.1700
Data Index: 1794185 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.1494. Min Act: -0.1700
Data Index: 5142529 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0244. Min Act: -0.1700
Data Index: 1107377 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0869. Min Act: -0.1700
Data Index: 8426377 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0869. Min Act: -0.1700
Data Index: 7529070 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0869. Min Act: -0.1700
Data Index: 1915102 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0244. Min Act: -0.1700
Data Index: 4123472 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0244. Min Act: -0.1700
Data Index: 3282932 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8994. Min Range: -10.8994
Max Act: 10.0244. Min Act: -0.1700
Data Index: 3397395 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8994. Min Range: -10.8994
Max Act: 9.9619. Min Act: -0.1700
Data Index: 2831570 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8994. Min Range: -10.8994
Max Act: 9.9619. Min Act: -0.1700
Data Index: 2528047 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8994. Min Range: -10.8994
Max Act: 9.9619. Min Act: -0.1700
Data Index: 585251 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19