Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.3132. Min Act: -0.1700
Data Index: 7192613 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.2507. Min Act: -0.1700
Data Index: 6827248 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.1257. Min Act: -0.1700
Data Index: 3174265 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0320. Min Act: -0.1700
Data Index: 7502645 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0320. Min Act: -0.1700
Data Index: 3255442 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 7676777 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0320. Min Act: -0.1700
Data Index: 1909642 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0320. Min Act: -0.1700
Data Index: 1854658 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0632. Min Act: -0.1700
Data Index: 8108943 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0320. Min Act: -0.1700
Data Index: 7848440 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3132. Min Range: -5.3132
Max Act: 4.9695. Min Act: -0.1700
Data Index: 8319807 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 3008080 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 2825852 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 213123 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 8598525 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 2893737 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3132. Min Range: -5.3132
Max Act: 4.9695. Min Act: -0.1700
Data Index: 507446 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0320. Min Act: -0.1700
Data Index: 3863586 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3132. Min Range: -5.3132
Max Act: 4.9695. Min Act: -0.1700
Data Index: 6690818 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3132. Min Range: -5.3132
Max Act: 5.0007. Min Act: -0.1700
Data Index: 3099453 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19