Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5352 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.4707. Min Act: -0.1700
Data Index: 971257 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.4394. Min Act: -0.1700
Data Index: 7781730 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.4394. Min Act: -0.1700
Data Index: 4777929 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.4082. Min Act: -0.1700
Data Index: 6381875 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.3769. Min Act: -0.1700
Data Index: 5441666 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.3769. Min Act: -0.1700
Data Index: 1753083 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.3457. Min Act: -0.1700
Data Index: 650713 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.3144. Min Act: -0.1700
Data Index: 434333 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.3144. Min Act: -0.1700
Data Index: 5133815 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.2832. Min Act: -0.1700
Data Index: 5176564 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.2207. Min Act: -0.1700
Data Index: 5694496 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.2519. Min Act: -0.1700
Data Index: 2483255 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.1894. Min Act: -0.1700
Data Index: 1390846 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.1894. Min Act: -0.1700
Data Index: 3860232 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.1582. Min Act: -0.1700
Data Index: 4695710 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.1582. Min Act: -0.1700
Data Index: 1274095 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.1269. Min Act: -0.1700
Data Index: 2655791 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.1269. Min Act: -0.1700
Data Index: 2304307 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.0644. Min Act: -0.1700
Data Index: 1685492 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4707. Min Range: -7.4707
Max Act: 7.0644. Min Act: -0.1700
Data Index: 6723858 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19