Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4964 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.6719. Min Act: -0.1700
Data Index: 2615174 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.6406. Min Act: -0.1700
Data Index: 7925127 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.5781. Min Act: -0.1700
Data Index: 7063522 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.5781. Min Act: -0.1700
Data Index: 2896637 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.5469. Min Act: -0.1700
Data Index: 636843 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.5156. Min Act: -0.1700
Data Index: 7260269 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.5156. Min Act: -0.1700
Data Index: 5669337 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4531. Min Act: -0.1700
Data Index: 8382252 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4219. Min Act: -0.1700
Data Index: 2908062 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4219. Min Act: -0.1700
Data Index: 7595923 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4219. Min Act: -0.1700
Data Index: 64574 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4219. Min Act: -0.1700
Data Index: 4618939 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4219. Min Act: -0.1700
Data Index: 4370613 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.4219. Min Act: -0.1700
Data Index: 8735359 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.3906. Min Act: -0.1700
Data Index: 6184576 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.3594. Min Act: -0.1700
Data Index: 8028006 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.3594. Min Act: -0.1700
Data Index: 6184575 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.3906. Min Act: -0.1700
Data Index: 5610682 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.3594. Min Act: -0.1700
Data Index: 3556728 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6719. Min Range: -5.6719
Max Act: 5.3906. Min Act: -0.1700
Data Index: 7980330 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19