Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.2094. Min Act: -0.1700
Data Index: 1923232 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1928. Min Act: -0.1700
Data Index: 5108653 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1595. Min Act: -0.1700
Data Index: 2647172 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1762. Min Act: -0.1700
Data Index: 7081645 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1595. Min Act: -0.1700
Data Index: 3985473 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1262. Min Act: -0.1700
Data Index: 3864039 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1262. Min Act: -0.1700
Data Index: 404193 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1262. Min Act: -0.1700
Data Index: 715461 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0927. Min Act: -0.1700
Data Index: 8044699 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.1094. Min Act: -0.1700
Data Index: 616141 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0927. Min Act: -0.1700
Data Index: 7673387 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0927. Min Act: -0.1700
Data Index: 2737317 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0759. Min Act: -0.1700
Data Index: 7550856 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0759. Min Act: -0.1700
Data Index: 6317495 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0759. Min Act: -0.1700
Data Index: 3587736 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0423. Min Act: -0.1699
Data Index: 1923233 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0591. Min Act: -0.1700
Data Index: 1923221 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0591. Min Act: -0.1700
Data Index: 7262702 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0591. Min Act: -0.1700
Data Index: 3497906 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2094. Min Range: -2.2094
Max Act: 2.0591. Min Act: -0.1700
Data Index: 2048802 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19