Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5469 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2878. Min Range: -9.2878
Max Act: 9.2878. Min Act: -0.1700
Data Index: 2306668 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2878. Min Range: -9.2878
Max Act: 9.2253. Min Act: -0.1700
Data Index: 2391908 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2878. Min Range: -9.2878
Max Act: 9.0378. Min Act: -0.1700
Data Index: 7326020 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.7253. Min Act: -0.1700
Data Index: 6160319 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.7878. Min Act: -0.1700
Data Index: 2261567 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.7253. Min Act: -0.1700
Data Index: 1991255 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.6628. Min Act: -0.1700
Data Index: 3755095 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.6628. Min Act: -0.1700
Data Index: 4806478 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.6003. Min Act: -0.1700
Data Index: 5622747 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.4753. Min Act: -0.1700
Data Index: 4787162 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.5378. Min Act: -0.1700
Data Index: 2635641 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.4128. Min Act: -0.1700
Data Index: 809999 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.4128. Min Act: -0.1700
Data Index: 6694181 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.4753. Min Act: -0.1700
Data Index: 1710294 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.3503. Min Act: -0.1700
Data Index: 5947326 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.2878. Min Act: -0.1700
Data Index: 6216507 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.2878. Min Act: -0.1700
Data Index: 6809252 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.2878. Min Act: -0.1700
Data Index: 419588 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.2878. Min Act: -0.1700
Data Index: 7706720 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2878. Min Range: -9.2878
Max Act: 8.2878. Min Act: -0.1700
Data Index: 976208 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19