Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.7597. Min Act: -0.1700
Data Index: 611994 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.6035. Min Act: -0.1700
Data Index: 611995 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.3222. Min Act: -0.1700
Data Index: 7447948 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.2909. Min Act: -0.1700
Data Index: 2473060 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.2909. Min Act: -0.1700
Data Index: 5565577 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.2597. Min Act: -0.1700
Data Index: 5339931 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1659. Min Act: -0.1700
Data Index: 2288476 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1347. Min Act: -0.1700
Data Index: 5565581 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1347. Min Act: -0.1700
Data Index: 5565580 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1972. Min Act: -0.1700
Data Index: 670034 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1659. Min Act: -0.1700
Data Index: 493050 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1347. Min Act: -0.1700
Data Index: 4993270 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1034. Min Act: -0.1700
Data Index: 8671303 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1034. Min Act: -0.1700
Data Index: 8689869 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1034. Min Act: -0.1700
Data Index: 2258269 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1034. Min Act: -0.1700
Data Index: 7066253 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1034. Min Act: -0.1700
Data Index: 1596294 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1347. Min Act: -0.1700
Data Index: 7273279 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.1034. Min Act: -0.1700
Data Index: 6889636 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7597. Min Range: -4.7597
Max Act: 4.0409. Min Act: -0.1700
Data Index: 2948524 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19