Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 665 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8039. Min Range: -9.8039
Max Act: 9.8039. Min Act: -0.1700
Data Index: 3628565 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8039. Min Range: -9.8039
Max Act: 9.3039. Min Act: -0.1700
Data Index: 6691524 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8039. Min Range: -9.8039
Max Act: 9.1789. Min Act: -0.1700
Data Index: 5909541 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.9914. Min Act: -0.1700
Data Index: 1932773 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.9289. Min Act: -0.1700
Data Index: 365752 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.8664. Min Act: -0.1700
Data Index: 3793324 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.8664. Min Act: -0.1700
Data Index: 8318620 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.8664. Min Act: -0.1700
Data Index: 1627695 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.8664. Min Act: -0.1700
Data Index: 5557219 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.8039. Min Act: -0.1700
Data Index: 1020229 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.8039. Min Act: -0.1700
Data Index: 4707032 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.7414. Min Act: -0.1700
Data Index: 4936697 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.7414. Min Act: -0.1700
Data Index: 6497422 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6789. Min Act: -0.1700
Data Index: 2239784 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6789. Min Act: -0.1700
Data Index: 1079591 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6789. Min Act: -0.1700
Data Index: 7101128 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6789. Min Act: -0.1700
Data Index: 6769047 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6789. Min Act: -0.1700
Data Index: 5944568 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6164. Min Act: -0.1700
Data Index: 2569219 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8039. Min Range: -9.8039
Max Act: 8.6164. Min Act: -0.1700
Data Index: 6225861 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19