Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.4399. Min Act: -0.1700
Data Index: 1956294 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2836. Min Act: -0.1700
Data Index: 6791713 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2836. Min Act: -0.1700
Data Index: 8281495 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2524. Min Act: -0.1700
Data Index: 6885024 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2836. Min Act: -0.1700
Data Index: 883697 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2524. Min Act: -0.1700
Data Index: 4563957 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2211. Min Act: -0.1700
Data Index: 2890888 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1898. Min Act: -0.1700
Data Index: 2813334 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.2211. Min Act: -0.1700
Data Index: 4516882 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1898. Min Act: -0.1700
Data Index: 2676639 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1898. Min Act: -0.1700
Data Index: 3249111 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 242928 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 5325057 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 3552166 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 2585094 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 7633205 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 8498964 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1273. Min Act: -0.1700
Data Index: 4129880 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1273. Min Act: -0.1700
Data Index: 4350393 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4399. Min Range: -4.4399
Max Act: 4.1586. Min Act: -0.1700
Data Index: 513623 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19