Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.9793. Min Act: -0.1700
Data Index: 123415 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.8543. Min Act: -0.1700
Data Index: 932196 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.9168. Min Act: -0.1700
Data Index: 5659740 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.9168. Min Act: -0.1700
Data Index: 5525193 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.5418. Min Act: -0.1700
Data Index: 820840 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.5418. Min Act: -0.1700
Data Index: 2136490 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.5418. Min Act: -0.1700
Data Index: 7470593 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.5418. Min Act: -0.1700
Data Index: 3478445 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.5418. Min Act: -0.1700
Data Index: 6568520 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4793. Min Act: -0.1700
Data Index: 8384295 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4793. Min Act: -0.1700
Data Index: 3094763 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4168. Min Act: -0.1700
Data Index: 3438712 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4168. Min Act: -0.1700
Data Index: 917409 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4168. Min Act: -0.1700
Data Index: 6321699 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4168. Min Act: -0.1700
Data Index: 8384312 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.4168. Min Act: -0.1700
Data Index: 7678351 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.3543. Min Act: -0.1700
Data Index: 3513920 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.3543. Min Act: -0.1700
Data Index: 7062313 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.3543. Min Act: -0.1700
Data Index: 3144743 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9793. Min Range: -8.9793
Max Act: 8.3543. Min Act: -0.1700
Data Index: 5833280 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19