Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.2434. Min Act: -0.1700
Data Index: 5236069 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.2120. Min Act: -0.1700
Data Index: 6491754 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.2277. Min Act: -0.1700
Data Index: 2841896 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1962. Min Act: -0.1700
Data Index: 7738386 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1962. Min Act: -0.1700
Data Index: 5435114 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1648. Min Act: -0.1700
Data Index: 3927527 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1648. Min Act: -0.1700
Data Index: 4538485 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1490. Min Act: -0.1700
Data Index: 775809 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1333. Min Act: -0.1700
Data Index: 5335094 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1333. Min Act: -0.1700
Data Index: 7968692 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1175. Min Act: -0.1700
Data Index: 4311510 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.1018. Min Act: -0.1700
Data Index: 4687006 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.0860. Min Act: -0.1700
Data Index: 8819766 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.0702. Min Act: -0.1700
Data Index: 4891402 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.0229. Min Act: -0.1700
Data Index: 7114373 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.0387. Min Act: -0.1700
Data Index: 7309595 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2434. Min Range: -3.2434
Max Act: 2.9913. Min Act: -0.1700
Data Index: 533963 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2434. Min Range: -3.2434
Max Act: 2.9913. Min Act: -0.1700
Data Index: 5319560 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.0071. Min Act: -0.1700
Data Index: 28383 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2434. Min Range: -3.2434
Max Act: 3.0071. Min Act: -0.1700
Data Index: 7722944 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19