Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0829. Min Range: -6.0829
Max Act: 6.0829. Min Act: -0.1700
Data Index: 87519 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.9579. Min Act: -0.1700
Data Index: 5586017 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.9267. Min Act: -0.1700
Data Index: 87514 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.8954. Min Act: -0.1700
Data Index: 7053651 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.8642. Min Act: -0.1700
Data Index: 5786377 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.8642. Min Act: -0.1700
Data Index: 3312405 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.8329. Min Act: -0.1700
Data Index: 87509 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.7704. Min Act: -0.1700
Data Index: 87515 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6767. Min Act: -0.1700
Data Index: 7531194 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.7079. Min Act: -0.1700
Data Index: 3753622 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4007296 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.7079. Min Act: -0.1700
Data Index: 3443371 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6767. Min Act: -0.1700
Data Index: 1968968 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6767. Min Act: -0.1700
Data Index: 6880422 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6767. Min Act: -0.1700
Data Index: 5641473 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6454. Min Act: -0.1700
Data Index: 4780929 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6454. Min Act: -0.1700
Data Index: 3674103 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6767. Min Act: -0.1700
Data Index: 452366 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.6142. Min Act: -0.1700
Data Index: 290045 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0829. Min Range: -6.0829
Max Act: 5.5829. Min Act: -0.1700
Data Index: 4097097 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19