Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.2889. Min Act: -0.1700
Data Index: 1972244 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.2889. Min Act: -0.1700
Data Index: 2703475 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.1639. Min Act: -0.1700
Data Index: 2545695 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.1327. Min Act: -0.1700
Data Index: 241765 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.1327. Min Act: -0.1700
Data Index: 3787059 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.1327. Min Act: -0.1700
Data Index: 2705934 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.0702. Min Act: -0.1700
Data Index: 8195414 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.0389. Min Act: -0.1700
Data Index: 5503603 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.0077. Min Act: -0.1700
Data Index: 658683 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2889. Min Range: -6.2889
Max Act: 6.0077. Min Act: -0.1700
Data Index: 8403570 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.9452. Min Act: -0.1700
Data Index: 6656940 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.9139. Min Act: -0.1700
Data Index: 5277437 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8827. Min Act: -0.1700
Data Index: 5155010 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8827. Min Act: -0.1700
Data Index: 2633881 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8827. Min Act: -0.1700
Data Index: 7580530 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8827. Min Act: -0.1700
Data Index: 3296961 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8827. Min Act: -0.1700
Data Index: 7317662 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8514. Min Act: -0.1700
Data Index: 4750416 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8514. Min Act: -0.1700
Data Index: 1503612 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2889. Min Range: -6.2889
Max Act: 5.8827. Min Act: -0.1700
Data Index: 6915750 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19