Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.5764. Min Act: -0.1700
Data Index: 3967627 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.5452. Min Act: -0.1700
Data Index: 2205962 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.5139. Min Act: -0.1700
Data Index: 3435502 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.4827. Min Act: -0.1700
Data Index: 1526651 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.5139. Min Act: -0.1700
Data Index: 1229509 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.5139. Min Act: -0.1700
Data Index: 2205963 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.4827. Min Act: -0.1700
Data Index: 999165 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.4514. Min Act: -0.1700
Data Index: 3981117 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.4202. Min Act: -0.1700
Data Index: 6577529 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.4202. Min Act: -0.1700
Data Index: 3612276 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.3577. Min Act: -0.1700
Data Index: 1471441 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.3577. Min Act: -0.1700
Data Index: 1025770 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.3577. Min Act: -0.1700
Data Index: 8125430 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.3264. Min Act: -0.1700
Data Index: 8126157 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.3264. Min Act: -0.1700
Data Index: 3086364 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.2639. Min Act: -0.1700
Data Index: 8742339 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.2952. Min Act: -0.1699
Data Index: 4907800 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.2952. Min Act: -0.1700
Data Index: 572601 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.2952. Min Act: -0.1700
Data Index: 8555789 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5764. Min Range: -5.5764
Max Act: 5.2639. Min Act: -0.1700
Data Index: 2297999 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19