Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.9328. Min Act: -0.1700
Data Index: 4509818 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.8703. Min Act: -0.1700
Data Index: 3647827 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.8703. Min Act: -0.1700
Data Index: 5641413 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.8078. Min Act: -0.1700
Data Index: 8611813 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.7140. Min Act: -0.1700
Data Index: 5185035 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.7453. Min Act: -0.1700
Data Index: 3229218 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.7140. Min Act: -0.1700
Data Index: 4496258 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 863978 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 8108656 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.6828. Min Act: -0.1700
Data Index: 6240248 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 7294559 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 5546309 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.6203. Min Act: -0.1700
Data Index: 8430799 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5890. Min Act: -0.1700
Data Index: 3534855 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5578. Min Act: -0.1700
Data Index: 198409 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5578. Min Act: -0.1700
Data Index: 5468442 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5578. Min Act: -0.1700
Data Index: 4301654 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 7461387 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5578. Min Act: -0.1700
Data Index: 3676994 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9328. Min Range: -5.9328
Max Act: 5.5265. Min Act: -0.1700
Data Index: 3432017 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19