Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.8532. Min Act: -0.1700
Data Index: 5840255 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.6344. Min Act: -0.1700
Data Index: 8215995 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.5719. Min Act: -0.1700
Data Index: 4192712 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.6032. Min Act: -0.1700
Data Index: 6781412 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.5094. Min Act: -0.1700
Data Index: 1132665 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4469. Min Act: -0.1700
Data Index: 3794516 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4469. Min Act: -0.1700
Data Index: 7001798 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4469. Min Act: -0.1700
Data Index: 1243155 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4469. Min Act: -0.1700
Data Index: 3768986 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 671804 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 2681820 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 3574063 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.4157. Min Act: -0.1700
Data Index: 5236865 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 4481534 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3844. Min Act: -0.1700
Data Index: 1990852 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 1209919 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 946390 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 1427333 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 7598518 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8532. Min Range: -4.8532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 8511025 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19