Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.9599. Min Act: -0.1700
Data Index: 5267049 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.8349. Min Act: -0.1700
Data Index: 5373746 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.8349. Min Act: -0.1700
Data Index: 4023876 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.8036. Min Act: -0.1700
Data Index: 730497 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7724. Min Act: -0.1700
Data Index: 3278081 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.8036. Min Act: -0.1700
Data Index: 5962191 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7724. Min Act: -0.1700
Data Index: 3356794 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7107563 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7724. Min Act: -0.1700
Data Index: 7894374 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7099. Min Act: -0.1700
Data Index: 7420297 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7099. Min Act: -0.1700
Data Index: 4598670 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.6786. Min Act: -0.1700
Data Index: 5654009 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8345980 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7411. Min Act: -0.1700
Data Index: 4874147 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.6786. Min Act: -0.1700
Data Index: 5473188 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.7099. Min Act: -0.1700
Data Index: 2103184 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.6786. Min Act: -0.1700
Data Index: 4245445 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.6786. Min Act: -0.1700
Data Index: 4545848 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.6474. Min Act: -0.1700
Data Index: 1596978 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9599. Min Range: -5.9599
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7743211 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19