Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 97 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.7960. Min Act: -0.1700
Data Index: 4289707 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.7615. Min Act: -0.1700
Data Index: 647117 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6749. Min Act: -0.1700
Data Index: 5478460 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6575. Min Act: -0.1700
Data Index: 8476400 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6052. Min Act: -0.1700
Data Index: 1314106 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6401. Min Act: -0.1700
Data Index: 255855 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5878. Min Act: -0.1700
Data Index: 4402067 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6052. Min Act: -0.1700
Data Index: 424247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6052. Min Act: -0.1700
Data Index: 4559688 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5878. Min Act: -0.1700
Data Index: 2926645 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.6052. Min Act: -0.1700
Data Index: 7613850 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5878. Min Act: -0.1700
Data Index: 2647305 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5528. Min Act: -0.1700
Data Index: 6756837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5528. Min Act: -0.1700
Data Index: 650437 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5353. Min Act: -0.1700
Data Index: 4249338 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5353. Min Act: -0.1700
Data Index: 3703031 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5528. Min Act: -0.1700
Data Index: 803309 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5353. Min Act: -0.1700
Data Index: 6147703 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5353. Min Act: -0.1700
Data Index: 8355314 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7960. Min Range: -1.7960
Max Act: 1.5353. Min Act: -0.1700
Data Index: 2131911 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19