Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.4862. Min Act: -0.1700
Data Index: 149688 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.2675. Min Act: -0.1700
Data Index: 6967357 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.2362. Min Act: -0.1700
Data Index: 6984449 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.2362. Min Act: -0.1700
Data Index: 3075173 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.2362. Min Act: -0.1700
Data Index: 5938626 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.2050. Min Act: -0.1700
Data Index: 8513777 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.2050. Min Act: -0.1700
Data Index: 6596009 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1737. Min Act: -0.1700
Data Index: 6235564 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1209146 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1032233 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1737. Min Act: -0.1700
Data Index: 4913289 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1112. Min Act: -0.1700
Data Index: 3967902 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1837636 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1112. Min Act: -0.1700
Data Index: 7115202 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1771330 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.0800. Min Act: -0.1700
Data Index: 6984735 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.0800. Min Act: -0.1700
Data Index: 326928 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.0487. Min Act: -0.1700
Data Index: 4366838 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.0487. Min Act: -0.1700
Data Index: 4360135 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4862. Min Range: -5.4862
Max Act: 5.0487. Min Act: -0.1700
Data Index: 4210992 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19