Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5722 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.9478. Min Act: -0.1700
Data Index: 6657630 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.8853. Min Act: -0.1700
Data Index: 1384782 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.8853. Min Act: -0.1700
Data Index: 2502140 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7916. Min Act: -0.1700
Data Index: 6333767 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7603. Min Act: -0.1700
Data Index: 6489894 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7916. Min Act: -0.1700
Data Index: 1122291 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7916. Min Act: -0.1700
Data Index: 4643736 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7916. Min Act: -0.1700
Data Index: 3406183 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7603. Min Act: -0.1700
Data Index: 1815179 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7603. Min Act: -0.1700
Data Index: 1867983 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.7291. Min Act: -0.1700
Data Index: 3473816 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6666. Min Act: -0.1700
Data Index: 8466587 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6978. Min Act: -0.1700
Data Index: 5245414 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6666. Min Act: -0.1700
Data Index: 3431335 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6978. Min Act: -0.1700
Data Index: 1078504 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6666. Min Act: -0.1700
Data Index: 7707680 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6666. Min Act: -0.1700
Data Index: 6495047 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6353. Min Act: -0.1700
Data Index: 4459227 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6353. Min Act: -0.1700
Data Index: 987484 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9478. Min Range: -5.9478
Max Act: 5.6353. Min Act: -0.1700
Data Index: 4773463 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19