Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0166. Min Range: -6.0166
Max Act: 6.0166. Min Act: -0.1700
Data Index: 1072178 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.9853. Min Act: -0.1700
Data Index: 8514902 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3986504 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.7978. Min Act: -0.1700
Data Index: 4907087 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.6728. Min Act: -0.1700
Data Index: 1322973 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.6416. Min Act: -0.1700
Data Index: 8610172 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.6416. Min Act: -0.1700
Data Index: 3003923 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.6103. Min Act: -0.1700
Data Index: 8514901 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5478. Min Act: -0.1700
Data Index: 1478592 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5478. Min Act: -0.1700
Data Index: 11618 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 2026578 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 3883789 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 6124971 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 4991581 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.4853. Min Act: -0.1700
Data Index: 2936977 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 99167 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.4853. Min Act: -0.1700
Data Index: 8494951 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.5166. Min Act: -0.1700
Data Index: 3158768 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.4541. Min Act: -0.1700
Data Index: 6302218 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0166. Min Range: -6.0166
Max Act: 5.4541. Min Act: -0.1700
Data Index: 6880554 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19