Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4862 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.7032. Min Act: -0.1700
Data Index: 5114021 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.6095. Min Act: -0.1700
Data Index: 942496 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.6095. Min Act: -0.1700
Data Index: 4600318 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.6095. Min Act: -0.1700
Data Index: 8571431 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.5470. Min Act: -0.1700
Data Index: 7981610 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.5470. Min Act: -0.1700
Data Index: 4265645 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.4220. Min Act: -0.1700
Data Index: 590006 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.4532. Min Act: -0.1700
Data Index: 4762481 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.4532. Min Act: -0.1700
Data Index: 600461 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3595. Min Act: -0.1700
Data Index: 7776955 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3595. Min Act: -0.1700
Data Index: 6415414 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3595. Min Act: -0.1700
Data Index: 411496 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3282. Min Act: -0.1700
Data Index: 8253900 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3282. Min Act: -0.1700
Data Index: 2079361 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.2970. Min Act: -0.1700
Data Index: 7548726 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3282. Min Act: -0.1700
Data Index: 4782161 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3282. Min Act: -0.1700
Data Index: 2428712 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.3282. Min Act: -0.1700
Data Index: 4030787 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.2970. Min Act: -0.1700
Data Index: 7761863 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7032. Min Range: -4.7032
Max Act: 4.2970. Min Act: -0.1700
Data Index: 7961460 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19