Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 191 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1596. Min Range: -8.1596
Max Act: 8.1596. Min Act: -0.1700
Data Index: 4025625 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1596. Min Range: -8.1596
Max Act: 8.0346. Min Act: -0.1700
Data Index: 3849629 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.9721. Min Act: -0.1700
Data Index: 1783099 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.9721. Min Act: -0.1700
Data Index: 8100539 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.9721. Min Act: -0.1700
Data Index: 5057413 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.9096. Min Act: -0.1700
Data Index: 7256137 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 4902788 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.9096. Min Act: -0.1700
Data Index: 2811104 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 5037385 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.7846. Min Act: -0.1700
Data Index: 6271421 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 6333928 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 2260702 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 156818 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 6818639 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 4507169 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 719152 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.9096. Min Act: -0.1700
Data Index: 260740 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 4680878 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 4320136 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1596. Min Range: -8.1596
Max Act: 7.8471. Min Act: -0.1700
Data Index: 797141 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19