Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.4025. Min Act: -0.1700
Data Index: 1917982 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.2150. Min Act: -0.1700
Data Index: 1837962 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.1213. Min Act: -0.1700
Data Index: 1268059 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.1213. Min Act: -0.1700
Data Index: 374077 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0900. Min Act: -0.1700
Data Index: 7789248 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.1213. Min Act: -0.1700
Data Index: 139561 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0900. Min Act: -0.1700
Data Index: 8037530 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0900. Min Act: -0.1700
Data Index: 2883349 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0588. Min Act: -0.1700
Data Index: 8230659 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7630153 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7128736 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 1728999 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 3906175 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9963. Min Act: -0.1700
Data Index: 1268060 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9963. Min Act: -0.1700
Data Index: 1412448 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9963. Min Act: -0.1700
Data Index: 2037701 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9963. Min Act: -0.1700
Data Index: 4658538 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 587375 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9338. Min Act: -0.1700
Data Index: 8478773 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9338. Min Act: -0.1700
Data Index: 5299744 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19