Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2750. Min Act: -0.1700
Data Index: 7062661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2437. Min Act: -0.1700
Data Index: 660346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2437. Min Act: -0.1700
Data Index: 6945434 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2437. Min Act: -0.1699
Data Index: 4451395 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2437. Min Act: -0.1700
Data Index: 6931457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2437. Min Act: -0.1700
Data Index: 8604964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2125. Min Act: -0.1700
Data Index: 3174027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2125. Min Act: -0.1700
Data Index: 3612048 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.2125. Min Act: -0.1700
Data Index: 1827253 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1812. Min Act: -0.1700
Data Index: 7181973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1812. Min Act: -0.1700
Data Index: 6603164 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1812. Min Act: -0.1700
Data Index: 5002598 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1812. Min Act: -0.1700
Data Index: 6772488 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1812. Min Act: -0.1700
Data Index: 7894141 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1812. Min Act: -0.1700
Data Index: 2372959 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1500. Min Act: -0.1700
Data Index: 6696840 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1500. Min Act: -0.1700
Data Index: 3279365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1500. Min Act: -0.1700
Data Index: 1259199 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1187. Min Act: -0.1700
Data Index: 6696842 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2750. Min Range: -6.2750
Max Act: 6.1187. Min Act: -0.1700
Data Index: 1242667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19