Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.6675. Min Act: -0.1700
Data Index: 5752781 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.3550. Min Act: -0.1700
Data Index: 961331 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2300. Min Act: -0.1700
Data Index: 1063282 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.3550. Min Act: -0.1700
Data Index: 1356366 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2925. Min Act: -0.1700
Data Index: 6479134 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.1675. Min Act: -0.1700
Data Index: 2474729 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2300. Min Act: -0.1700
Data Index: 2821024 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2300. Min Act: -0.1700
Data Index: 992972 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2300. Min Act: -0.1700
Data Index: 2865132 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2300. Min Act: -0.1700
Data Index: 7842209 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.2300. Min Act: -0.1700
Data Index: 6467363 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.1675. Min Act: -0.1700
Data Index: 5884657 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.1675. Min Act: -0.1700
Data Index: 2194062 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.1050. Min Act: -0.1700
Data Index: 6401586 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.0425. Min Act: -0.1700
Data Index: 6514314 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6675. Min Range: -8.6675
Max Act: 7.9800. Min Act: -0.1700
Data Index: 4653348 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.0425. Min Act: -0.1700
Data Index: 7150802 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6675. Min Range: -8.6675
Max Act: 8.0425. Min Act: -0.1700
Data Index: 6253616 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6675. Min Range: -8.6675
Max Act: 7.9800. Min Act: -0.1700
Data Index: 4813756 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6675. Min Range: -8.6675
Max Act: 7.9488. Min Act: -0.1700
Data Index: 1066334 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19