Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.7434. Min Act: -0.1700
Data Index: 6474206 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.5559. Min Act: -0.1700
Data Index: 4729228 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.4621. Min Act: -0.1700
Data Index: 824714 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.4621. Min Act: -0.1700
Data Index: 3287350 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.4621. Min Act: -0.1700
Data Index: 5410914 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.4621. Min Act: -0.1700
Data Index: 8022148 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.3996. Min Act: -0.1700
Data Index: 2813891 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.3996. Min Act: -0.1700
Data Index: 7148697 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.3996. Min Act: -0.1700
Data Index: 2189915 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.3371. Min Act: -0.1700
Data Index: 8495224 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.3059. Min Act: -0.1700
Data Index: 1106991 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.2746. Min Act: -0.1700
Data Index: 2070930 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.3059. Min Act: -0.1700
Data Index: 5794300 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.2746. Min Act: -0.1700
Data Index: 6016081 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.2746. Min Act: -0.1700
Data Index: 7364991 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.2746. Min Act: -0.1700
Data Index: 7044604 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.1809. Min Act: -0.1700
Data Index: 5318698 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.2121. Min Act: -0.1700
Data Index: 7118172 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.1496. Min Act: -0.1700
Data Index: 6677598 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7434. Min Range: -7.7434
Max Act: 7.1184. Min Act: -0.1700
Data Index: 1393625 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19