Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0084. Min Range: -6.0084
Max Act: 6.0084. Min Act: -0.1700
Data Index: 4865517 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.9146. Min Act: -0.1700
Data Index: 6408674 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.8834. Min Act: -0.1700
Data Index: 5056486 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.8834. Min Act: -0.1700
Data Index: 3053610 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.9146. Min Act: -0.1700
Data Index: 5968742 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.8209. Min Act: -0.1700
Data Index: 4493173 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.7271. Min Act: -0.1700
Data Index: 4778171 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.8209. Min Act: -0.1700
Data Index: 8103913 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.7271. Min Act: -0.1700
Data Index: 8307459 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.6959. Min Act: -0.1700
Data Index: 2577840 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.6646. Min Act: -0.1700
Data Index: 7300352 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.6334. Min Act: -0.1700
Data Index: 5934013 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.6334. Min Act: -0.1700
Data Index: 2246726 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.6334. Min Act: -0.1700
Data Index: 4777619 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.6021. Min Act: -0.1700
Data Index: 7145694 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.5709. Min Act: -0.1700
Data Index: 6232768 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5084783 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.5396. Min Act: -0.1700
Data Index: 3426488 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.5709. Min Act: -0.1700
Data Index: 2452292 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0084. Min Range: -6.0084
Max Act: 5.5084. Min Act: -0.1700
Data Index: 5465671 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19