Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1128 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8423. Min Act: -0.1700
Data Index: 632544 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8736. Min Act: -0.1700
Data Index: 3059444 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8736. Min Act: -0.1700
Data Index: 7566273 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8736. Min Act: -0.1700
Data Index: 6769027 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8736. Min Act: -0.1700
Data Index: 8193676 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8736. Min Act: -0.1700
Data Index: 3997671 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8736. Min Act: -0.1700
Data Index: 8524174 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8423. Min Act: -0.1700
Data Index: 6182012 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8423. Min Act: -0.1700
Data Index: 2149278 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8423. Min Act: -0.1700
Data Index: 4164370 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8111. Min Act: -0.1700
Data Index: 1636781 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8111. Min Act: -0.1700
Data Index: 5705777 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8423. Min Act: -0.1700
Data Index: 7494346 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.7486. Min Act: -0.1700
Data Index: 3224141 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.8111. Min Act: -0.1700
Data Index: 3763 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.7798. Min Act: -0.1700
Data Index: 1452795 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.7798. Min Act: -0.1700
Data Index: 1729404 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.7798. Min Act: -0.1700
Data Index: 6607894 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.7173. Min Act: -0.1700
Data Index: 4850151 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8736. Min Range: -4.8736
Max Act: 4.7173. Min Act: -0.1700
Data Index: 1075945 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19