Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.9578. Min Act: -0.1700
Data Index: 6594882 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.8015. Min Act: -0.1700
Data Index: 7155756 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.7390. Min Act: -0.1700
Data Index: 6848578 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.4265. Min Act: -0.1700
Data Index: 7941321 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.4578. Min Act: -0.1700
Data Index: 5572865 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3953. Min Act: -0.1700
Data Index: 7496538 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3953. Min Act: -0.1700
Data Index: 7941319 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3640. Min Act: -0.1700
Data Index: 814298 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3640. Min Act: -0.1700
Data Index: 7496552 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3328. Min Act: -0.1700
Data Index: 8432486 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3328. Min Act: -0.1700
Data Index: 5440424 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3328. Min Act: -0.1700
Data Index: 7496555 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3015. Min Act: -0.1700
Data Index: 7496553 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3328. Min Act: -0.1700
Data Index: 7496554 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3015. Min Act: -0.1700
Data Index: 6638412 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3015. Min Act: -0.1700
Data Index: 7038521 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3015. Min Act: -0.1700
Data Index: 7596849 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.3328. Min Act: -0.1700
Data Index: 2419776 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.2703. Min Act: -0.1700
Data Index: 7496540 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9578. Min Range: -7.9578
Max Act: 7.2390. Min Act: -0.1700
Data Index: 2419775 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19