Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.8119. Min Act: -0.1700
Data Index: 4230096 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.5619. Min Act: -0.1700
Data Index: 1846526 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.4994. Min Act: -0.1700
Data Index: 1132576 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.4369. Min Act: -0.1700
Data Index: 3989600 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.4057. Min Act: -0.1700
Data Index: 2593937 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.2807. Min Act: -0.1700
Data Index: 7339669 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.2807. Min Act: -0.1700
Data Index: 3675291 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.2494. Min Act: -0.1700
Data Index: 6310573 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.2182. Min Act: -0.1700
Data Index: 2593928 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.2182. Min Act: -0.1700
Data Index: 3836681 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.2182. Min Act: -0.1700
Data Index: 450823 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.1869. Min Act: -0.1700
Data Index: 7307993 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.1869. Min Act: -0.1700
Data Index: 4530976 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.1869. Min Act: -0.1700
Data Index: 2932633 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.1869. Min Act: -0.1700
Data Index: 317924 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.1557. Min Act: -0.1700
Data Index: 1733891 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.1244. Min Act: -0.1700
Data Index: 7651933 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.0619. Min Act: -0.1700
Data Index: 6179272 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.0932. Min Act: -0.1700
Data Index: 3421917 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8119. Min Range: -7.8119
Max Act: 7.0619. Min Act: -0.1700
Data Index: 2554870 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19