Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0748. Min Range: -9.0748
Max Act: 9.0748. Min Act: -0.1700
Data Index: 6039546 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.8873. Min Act: -0.1700
Data Index: 1668763 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.9498. Min Act: -0.1700
Data Index: 1025787 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.5123. Min Act: -0.1700
Data Index: 2073765 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.4498. Min Act: -0.1700
Data Index: 1967618 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.5123. Min Act: -0.1700
Data Index: 5784211 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.3248. Min Act: -0.1700
Data Index: 3696677 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.1685. Min Act: -0.1700
Data Index: 6498536 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0748. Min Range: -9.0748
Max Act: 8.0435. Min Act: -0.1700
Data Index: 5784210 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9810. Min Act: -0.1700
Data Index: 3141769 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9810. Min Act: -0.1700
Data Index: 507622 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9810. Min Act: -0.1700
Data Index: 2606121 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9810. Min Act: -0.1700
Data Index: 2882327 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9498. Min Act: -0.1700
Data Index: 4604418 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9498. Min Act: -0.1700
Data Index: 8239708 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9185. Min Act: -0.1700
Data Index: 6112597 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.9185. Min Act: -0.1700
Data Index: 6989587 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.8873. Min Act: -0.1700
Data Index: 5784209 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.7623. Min Act: -0.1700
Data Index: 6333232 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0748. Min Range: -9.0748
Max Act: 7.8248. Min Act: -0.1700
Data Index: 4666159 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19