Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0174. Min Range: -6.0174
Max Act: 6.0174. Min Act: -0.1700
Data Index: 4911463 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.9861. Min Act: -0.1700
Data Index: 546238 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.9549. Min Act: -0.1700
Data Index: 1480067 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.9549. Min Act: -0.1700
Data Index: 197923 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.9236. Min Act: -0.1700
Data Index: 8402015 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.9236. Min Act: -0.1700
Data Index: 4635313 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 8643478 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 341155 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 980717 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 5056904 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 6918737 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8611. Min Act: -0.1700
Data Index: 146092 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 8809244 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8611. Min Act: -0.1700
Data Index: 1682839 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8924. Min Act: -0.1700
Data Index: 2753674 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8611. Min Act: -0.1700
Data Index: 6160846 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8299. Min Act: -0.1700
Data Index: 7364158 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8299. Min Act: -0.1700
Data Index: 2655066 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8299. Min Act: -0.1700
Data Index: 5570508 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0174. Min Range: -6.0174
Max Act: 5.8299. Min Act: -0.1700
Data Index: 3837532 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19