Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1699 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.8396. Min Act: -0.1700
Data Index: 5841705 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.6521. Min Act: -0.1700
Data Index: 8336589 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.5896. Min Act: -0.1700
Data Index: 5043952 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.3396. Min Act: -0.1700
Data Index: 3620903 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.2771. Min Act: -0.1700
Data Index: 413204 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.2146. Min Act: -0.1700
Data Index: 6299029 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 137570 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 1174884 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 7823222 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0896. Min Act: -0.1700
Data Index: 7491471 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0896. Min Act: -0.1700
Data Index: 5841708 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0896. Min Act: -0.1700
Data Index: 8097542 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0896. Min Act: -0.1700
Data Index: 7163681 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9958. Min Act: -0.1700
Data Index: 6783771 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9646. Min Act: -0.1700
Data Index: 1430433 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9333. Min Act: -0.1700
Data Index: 3946233 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9333. Min Act: -0.1700
Data Index: 2964512 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9333. Min Act: -0.1700
Data Index: 4248603 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9021. Min Act: -0.1700
Data Index: 264310 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8396. Min Range: -8.8396
Max Act: 7.9021. Min Act: -0.1700
Data Index: 5284838 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19