Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0812. Min Range: -6.0812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8047531 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.9250. Min Act: -0.1700
Data Index: 5936607 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.8625. Min Act: -0.1700
Data Index: 126316 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3086486 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.5812. Min Act: -0.1700
Data Index: 4067232 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.5812. Min Act: -0.1700
Data Index: 7696136 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.5812. Min Act: -0.1700
Data Index: 925230 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.5500. Min Act: -0.1700
Data Index: 8468283 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.5187. Min Act: -0.1700
Data Index: 1019209 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3085151 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3278883 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4562. Min Act: -0.1700
Data Index: 5346690 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 3780019 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 3319898 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 426235 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 1409860 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.3937. Min Act: -0.1700
Data Index: 7815652 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.3937. Min Act: -0.1700
Data Index: 6186358 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.3937. Min Act: -0.1700
Data Index: 2687038 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.3312. Min Act: -0.1700
Data Index: 3004165 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19