Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.2756. Min Act: -0.1700
Data Index: 3688052 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.1819. Min Act: -0.1700
Data Index: 832117 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.1506. Min Act: -0.1700
Data Index: 5220924 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.1506. Min Act: -0.1700
Data Index: 3473 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.1506. Min Act: -0.1700
Data Index: 924761 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.1194. Min Act: -0.1700
Data Index: 2962595 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.0881. Min Act: -0.1700
Data Index: 4944523 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2756. Min Range: -8.2756
Max Act: 8.0256. Min Act: -0.1700
Data Index: 7085497 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.9944. Min Act: -0.1700
Data Index: 2929491 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.9631. Min Act: -0.1700
Data Index: 2892339 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.9006. Min Act: -0.1700
Data Index: 4983276 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.8694. Min Act: -0.1700
Data Index: 7302116 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.8381. Min Act: -0.1700
Data Index: 6740548 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.8069. Min Act: -0.1700
Data Index: 2296895 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.8381. Min Act: -0.1700
Data Index: 4264517 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.7756. Min Act: -0.1700
Data Index: 3760615 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.7756. Min Act: -0.1700
Data Index: 6181020 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.7131. Min Act: -0.1700
Data Index: 5061262 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.6819. Min Act: -0.1700
Data Index: 7273494 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2756. Min Range: -8.2756
Max Act: 7.6819. Min Act: -0.1700
Data Index: 6529655 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19