Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5503 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.8744. Min Act: -0.1700
Data Index: 8296837 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.4994. Min Act: -0.1700
Data Index: 4503555 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.4681. Min Act: -0.1700
Data Index: 2431505 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.4056. Min Act: -0.1700
Data Index: 5882083 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.3743. Min Act: -0.1700
Data Index: 4036769 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.4056. Min Act: -0.1700
Data Index: 3712646 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.3431. Min Act: -0.1700
Data Index: 3540146 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.3118. Min Act: -0.1700
Data Index: 3821989 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2493. Min Act: -0.1700
Data Index: 3742487 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2806. Min Act: -0.1700
Data Index: 6139984 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 2393740 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2493. Min Act: -0.1700
Data Index: 3135119 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2493. Min Act: -0.1700
Data Index: 3910462 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 339574 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.1868. Min Act: -0.1700
Data Index: 6411824 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 1218435 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 4503554 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.1868. Min Act: -0.1700
Data Index: 3712645 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.1556. Min Act: -0.1700
Data Index: 2031045 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8744. Min Range: -4.8744
Max Act: 4.1868. Min Act: -0.1700
Data Index: 8296835 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19