Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1162 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.3679. Min Act: -0.1700
Data Index: 5665001 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.3054. Min Act: -0.1700
Data Index: 5665000 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.3054. Min Act: -0.1700
Data Index: 1894260 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.2429. Min Act: -0.1700
Data Index: 8433838 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.2741. Min Act: -0.1700
Data Index: 7355568 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1804. Min Act: -0.1700
Data Index: 417929 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1804. Min Act: -0.1700
Data Index: 7310548 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1804. Min Act: -0.1700
Data Index: 2883428 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1491. Min Act: -0.1700
Data Index: 329255 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1179. Min Act: -0.1700
Data Index: 2883427 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1491. Min Act: -0.1700
Data Index: 3441836 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1491. Min Act: -0.1700
Data Index: 1586605 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1491. Min Act: -0.1700
Data Index: 3249999 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.1179. Min Act: -0.1700
Data Index: 7748711 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.0866. Min Act: -0.1700
Data Index: 555754 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.0866. Min Act: -0.1700
Data Index: 7765490 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.0241. Min Act: -0.1700
Data Index: 3595891 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.0554. Min Act: -0.1700
Data Index: 6851832 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3679. Min Range: -6.3679
Max Act: 5.9929. Min Act: -0.1700
Data Index: 6923999 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3679. Min Range: -6.3679
Max Act: 6.0554. Min Act: -0.1700
Data Index: 2663400 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19