Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5445 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.1165. Min Act: -0.1700
Data Index: 5033767 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0853. Min Act: -0.1700
Data Index: 4771774 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0540. Min Act: -0.1700
Data Index: 5843319 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0228. Min Act: -0.1700
Data Index: 3132565 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0228. Min Act: -0.1700
Data Index: 1102595 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0228. Min Act: -0.1700
Data Index: 38876 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0228. Min Act: -0.1700
Data Index: 1037768 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1165. Min Range: -5.1165
Max Act: 5.0228. Min Act: -0.1700
Data Index: 6580869 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.9915. Min Act: -0.1700
Data Index: 2614971 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.9603. Min Act: -0.1700
Data Index: 2468584 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 7657534 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.9290. Min Act: -0.1700
Data Index: 2397549 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.9290. Min Act: -0.1700
Data Index: 8509148 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 415461 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 1897030 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 4799080 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 5380304 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 2377613 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 1751091 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1165. Min Range: -5.1165
Max Act: 4.8978. Min Act: -0.1700
Data Index: 3127050 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19