Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1522. Min Range: -8.1522
Max Act: 8.1522. Min Act: -0.1700
Data Index: 3844104 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1522. Min Range: -8.1522
Max Act: 8.0272. Min Act: -0.1700
Data Index: 3748893 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.9647. Min Act: -0.1700
Data Index: 3143336 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1522. Min Range: -8.1522
Max Act: 8.0272. Min Act: -0.1700
Data Index: 7586964 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.7772. Min Act: -0.1700
Data Index: 8252725 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.7147. Min Act: -0.1700
Data Index: 4846521 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.7147. Min Act: -0.1700
Data Index: 2777960 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.7147. Min Act: -0.1700
Data Index: 7030803 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.6522. Min Act: -0.1700
Data Index: 6131274 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.6522. Min Act: -0.1700
Data Index: 3511666 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.5585. Min Act: -0.1700
Data Index: 2407220 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.5585. Min Act: -0.1700
Data Index: 1198711 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4960. Min Act: -0.1700
Data Index: 2063925 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4960. Min Act: -0.1700
Data Index: 6575898 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4960. Min Act: -0.1700
Data Index: 3065647 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4647. Min Act: -0.1700
Data Index: 1834763 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4647. Min Act: -0.1700
Data Index: 8228942 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4335. Min Act: -0.1700
Data Index: 5610185 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4022. Min Act: -0.1700
Data Index: 4802296 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1522. Min Range: -8.1522
Max Act: 7.4022. Min Act: -0.1700
Data Index: 3757937 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19