Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.9643. Min Act: -0.1700
Data Index: 2386162 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.7768. Min Act: -0.1700
Data Index: 8087122 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.6205. Min Act: -0.1700
Data Index: 5673546 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.6205. Min Act: -0.1700
Data Index: 4953987 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.4955. Min Act: -0.1700
Data Index: 5661773 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.4018. Min Act: -0.1700
Data Index: 5734633 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.4018. Min Act: -0.1700
Data Index: 2293601 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.2768. Min Act: -0.1700
Data Index: 865404 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.2455. Min Act: -0.1700
Data Index: 4113837 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.2143. Min Act: -0.1700
Data Index: 3955527 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.1830. Min Act: -0.1700
Data Index: 1855648 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.1830. Min Act: -0.1700
Data Index: 5607893 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.1205. Min Act: -0.1700
Data Index: 823693 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0893. Min Act: -0.1700
Data Index: 5636123 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0893. Min Act: -0.1700
Data Index: 423224 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3908492 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0893. Min Act: -0.1700
Data Index: 8491870 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 4896313 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 5121950 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9643. Min Range: -6.9643
Max Act: 6.0580. Min Act: -0.1700
Data Index: 768672 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19