Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.8333. Min Act: -0.1700
Data Index: 5774767 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.3646. Min Act: -0.1700
Data Index: 1167499 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.2083. Min Act: -0.1700
Data Index: 8023726 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1458. Min Act: -0.1700
Data Index: 6703991 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4750304 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.1146. Min Act: -0.1700
Data Index: 7871068 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.0833. Min Act: -0.1700
Data Index: 2056545 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.0208. Min Act: -0.1700
Data Index: 2216615 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.0208. Min Act: -0.1700
Data Index: 2305423 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8333. Min Range: -6.8333
Max Act: 6.0521. Min Act: -0.1700
Data Index: 8588245 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9583. Min Act: -0.1700
Data Index: 2335571 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9583. Min Act: -0.1700
Data Index: 2885990 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9896. Min Act: -0.1700
Data Index: 7651183 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9583. Min Act: -0.1700
Data Index: 5540747 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9271. Min Act: -0.1700
Data Index: 4241185 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9271. Min Act: -0.1700
Data Index: 8113414 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9271. Min Act: -0.1700
Data Index: 2760115 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.9271. Min Act: -0.1700
Data Index: 5308680 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.8958. Min Act: -0.1700
Data Index: 683567 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8333. Min Range: -6.8333
Max Act: 5.8958. Min Act: -0.1700
Data Index: 1129930 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19