Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1731 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.3192. Min Act: -0.1700
Data Index: 4632966 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.2567. Min Act: -0.1700
Data Index: 1893472 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.1629. Min Act: -0.1700
Data Index: 4458673 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.1629. Min Act: -0.1700
Data Index: 283606 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.1317. Min Act: -0.1700
Data Index: 7341397 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.1004. Min Act: -0.1700
Data Index: 6689090 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0692. Min Act: -0.1700
Data Index: 3290025 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0692. Min Act: -0.1700
Data Index: 7767177 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0692. Min Act: -0.1700
Data Index: 8606688 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0379. Min Act: -0.1700
Data Index: 5398539 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0379. Min Act: -0.1700
Data Index: 5182604 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0379. Min Act: -0.1700
Data Index: 8607493 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0067. Min Act: -0.1700
Data Index: 3751051 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0067. Min Act: -0.1700
Data Index: 1758311 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3192. Min Range: -4.3192
Max Act: 3.9754. Min Act: -0.1700
Data Index: 2617785 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3192. Min Range: -4.3192
Max Act: 3.9754. Min Act: -0.1700
Data Index: 4731237 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3192. Min Range: -4.3192
Max Act: 3.9754. Min Act: -0.1700
Data Index: 4964541 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3192. Min Range: -4.3192
Max Act: 4.0067. Min Act: -0.1700
Data Index: 828377 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3192. Min Range: -4.3192
Max Act: 3.9754. Min Act: -0.1700
Data Index: 569577 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3192. Min Range: -4.3192
Max Act: 3.9754. Min Act: -0.1700
Data Index: 5187115 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19