Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.8233. Min Act: -0.1700
Data Index: 4955285 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6983. Min Act: -0.1700
Data Index: 6314647 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6983. Min Act: -0.1700
Data Index: 6779863 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6983. Min Act: -0.1700
Data Index: 7520408 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6671. Min Act: -0.1700
Data Index: 7777999 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6358. Min Act: -0.1700
Data Index: 1480406 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6046. Min Act: -0.1700
Data Index: 6579674 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6046. Min Act: -0.1700
Data Index: 7006606 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1957192 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 6474748 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 6370969 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.6046. Min Act: -0.1700
Data Index: 6882016 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 4882342 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 3436039 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5733. Min Act: -0.1700
Data Index: 7547388 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5108. Min Act: -0.1700
Data Index: 702948 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5108. Min Act: -0.1700
Data Index: 3097746 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5108. Min Act: -0.1700
Data Index: 5772349 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.5108. Min Act: -0.1700
Data Index: 6028190 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8233. Min Range: -5.8233
Max Act: 5.4796. Min Act: -0.1700
Data Index: 2781068 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19