Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.9248. Min Act: -0.1700
Data Index: 205245 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.6748. Min Act: -0.1700
Data Index: 5972265 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.6748. Min Act: -0.1699
Data Index: 2131272 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.6748. Min Act: -0.1700
Data Index: 2084716 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.5498. Min Act: -0.1700
Data Index: 4596908 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4873. Min Act: -0.1700
Data Index: 5972266 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4873. Min Act: -0.1700
Data Index: 5972264 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4873. Min Act: -0.1700
Data Index: 768024 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4873. Min Act: -0.1700
Data Index: 4923229 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4248. Min Act: -0.1700
Data Index: 2833170 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4248. Min Act: -0.1700
Data Index: 7094261 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4248. Min Act: -0.1700
Data Index: 1604951 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4248. Min Act: -0.1700
Data Index: 4686868 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4248. Min Act: -0.1700
Data Index: 1381376 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.3623. Min Act: -0.1700
Data Index: 8463531 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.3623. Min Act: -0.1700
Data Index: 6899258 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.3623. Min Act: -0.1700
Data Index: 6899248 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.4248. Min Act: -0.1700
Data Index: 6754153 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.3623. Min Act: -0.1700
Data Index: 3271625 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.9248. Min Range: -16.9248
Max Act: 16.3623. Min Act: -0.1700
Data Index: 3160248 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19