Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5629. Min Range: -7.5629
Max Act: 7.5629. Min Act: -0.1700
Data Index: 1811457 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5629. Min Range: -7.5629
Max Act: 7.1879. Min Act: -0.1700
Data Index: 8655864 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5629. Min Range: -7.5629
Max Act: 7.0629. Min Act: -0.1700
Data Index: 7185105 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5629. Min Range: -7.5629
Max Act: 7.0317. Min Act: -0.1700
Data Index: 4242305 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.9692. Min Act: -0.1700
Data Index: 3075247 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.9067. Min Act: -0.1700
Data Index: 5730597 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.9379. Min Act: -0.1700
Data Index: 6864233 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.9067. Min Act: -0.1700
Data Index: 4533639 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.9067. Min Act: -0.1700
Data Index: 7334553 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.8754. Min Act: -0.1700
Data Index: 3826877 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3268152 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.7504. Min Act: -0.1700
Data Index: 6986265 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.7817. Min Act: -0.1700
Data Index: 2610785 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.7192. Min Act: -0.1700
Data Index: 3770486 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.7192. Min Act: -0.1700
Data Index: 3840646 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.6879. Min Act: -0.1700
Data Index: 656658 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.6879. Min Act: -0.1700
Data Index: 2682766 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.6879. Min Act: -0.1700
Data Index: 1317245 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.6254. Min Act: -0.1700
Data Index: 5217166 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5629. Min Range: -7.5629
Max Act: 6.6254. Min Act: -0.1700
Data Index: 5480977 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19