Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3589. Min Range: -4.3589
Max Act: 4.3589. Min Act: -0.1700
Data Index: 4307287 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3589. Min Range: -4.3589
Max Act: 4.0464. Min Act: -0.1700
Data Index: 4831384 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9839. Min Act: -0.1700
Data Index: 162358 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9839. Min Act: -0.1700
Data Index: 8641262 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9526. Min Act: -0.1700
Data Index: 5332551 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9526. Min Act: -0.1700
Data Index: 8798145 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9213. Min Act: -0.1700
Data Index: 5901405 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9213. Min Act: -0.1700
Data Index: 1344305 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9213. Min Act: -0.1700
Data Index: 3927702 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8901. Min Act: -0.1700
Data Index: 1307935 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.9213. Min Act: -0.1700
Data Index: 8415948 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8588. Min Act: -0.1700
Data Index: 4646608 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8588. Min Act: -0.1700
Data Index: 7597228 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8588. Min Act: -0.1700
Data Index: 8101577 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1361011 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8588. Min Act: -0.1700
Data Index: 8246949 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8588. Min Act: -0.1700
Data Index: 8754692 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.8275. Min Act: -0.1700
Data Index: 7459698 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.7963. Min Act: -0.1700
Data Index: 1361012 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3589. Min Range: -4.3589
Max Act: 3.7963. Min Act: -0.1700
Data Index: 237250 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19