Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.7143. Min Act: -0.1700
Data Index: 472868 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.6204. Min Act: -0.1700
Data Index: 1113608 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.6204. Min Act: -0.1700
Data Index: 5509498 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5891. Min Act: -0.1700
Data Index: 1056658 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 4961158 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 5509493 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 7670378 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 6154684 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 6268575 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 2649221 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5578. Min Act: -0.1700
Data Index: 472889 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5265. Min Act: -0.1700
Data Index: 6268577 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5265. Min Act: -0.1700
Data Index: 6459071 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5265. Min Act: -0.1700
Data Index: 5381007 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.5265. Min Act: -0.1700
Data Index: 5883490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.4952. Min Act: -0.1700
Data Index: 3278741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.4952. Min Act: -0.1700
Data Index: 3935035 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.4795. Min Act: -0.1700
Data Index: 4593382 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.4952. Min Act: -0.1700
Data Index: 202092 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7143. Min Range: -3.7143
Max Act: 3.4952. Min Act: -0.1700
Data Index: 4593381 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19