Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.6536. Min Act: -0.1700
Data Index: 2751321 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.5911. Min Act: -0.1700
Data Index: 2751323 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.5286. Min Act: -0.1700
Data Index: 3999999 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.5286. Min Act: -0.1700
Data Index: 740319 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.5286. Min Act: -0.1700
Data Index: 5861499 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 2197445 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 7656066 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 2561784 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 1916602 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 7022794 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 2751322 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4661. Min Act: -0.1700
Data Index: 8584066 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 1620257 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4661. Min Act: -0.1700
Data Index: 3704462 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4661. Min Act: -0.1700
Data Index: 8476609 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4974. Min Act: -0.1700
Data Index: 8043009 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4661. Min Act: -0.1700
Data Index: 7281545 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4349. Min Act: -0.1700
Data Index: 4196329 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4349. Min Act: -0.1700
Data Index: 7156232 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6536. Min Range: -4.6536
Max Act: 4.4349. Min Act: -0.1700
Data Index: 564125 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19