Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5502 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.9952. Min Act: -0.1700
Data Index: 5290542 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.8702. Min Act: -0.1700
Data Index: 5198382 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.7452. Min Act: -0.1700
Data Index: 2518686 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.7139. Min Act: -0.1700
Data Index: 3252152 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.7139. Min Act: -0.1700
Data Index: 8297056 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6827. Min Act: -0.1700
Data Index: 6338066 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5466425 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6514. Min Act: -0.1700
Data Index: 8482407 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6514. Min Act: -0.1700
Data Index: 4741305 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6514. Min Act: -0.1700
Data Index: 2379233 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.6514. Min Act: -0.1700
Data Index: 2039430 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 2264281 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5889. Min Act: -0.1700
Data Index: 364242 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5889. Min Act: -0.1700
Data Index: 6676651 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5889. Min Act: -0.1700
Data Index: 106021 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5889. Min Act: -0.1700
Data Index: 1131626 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 6978221 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 5365585 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 7733753 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9952. Min Range: -5.9952
Max Act: 5.5577. Min Act: -0.1700
Data Index: 3661564 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19