Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.8306. Min Act: -0.1700
Data Index: 7034495 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.3931. Min Act: -0.1700
Data Index: 8128826 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.1431. Min Act: -0.1700
Data Index: 6536516 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.1431. Min Act: -0.1700
Data Index: 4255704 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.0181. Min Act: -0.1700
Data Index: 2702426 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.0181. Min Act: -0.1700
Data Index: 5484835 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.0181. Min Act: -0.1700
Data Index: 930953 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.0181. Min Act: -0.1700
Data Index: 5791919 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.0181. Min Act: -0.1700
Data Index: 7406277 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8306. Min Range: -9.8306
Max Act: 9.0181. Min Act: -0.1700
Data Index: 3041855 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 5017507 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 5463384 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 6902442 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 1821935 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 4988137 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 7625868 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 1370568 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.9556. Min Act: -0.1700
Data Index: 2545875 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.8306. Min Act: -0.1700
Data Index: 7367733 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8306. Min Range: -9.8306
Max Act: 8.8931. Min Act: -0.1700
Data Index: 3300315 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19