Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.7877. Min Act: -0.1700
Data Index: 3623292 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.7565. Min Act: -0.1700
Data Index: 2302431 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6940. Min Act: -0.1700
Data Index: 5674439 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6940. Min Act: -0.1700
Data Index: 3919196 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6627. Min Act: -0.1700
Data Index: 6772941 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6315. Min Act: -0.1700
Data Index: 1637381 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6315. Min Act: -0.1700
Data Index: 6850784 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6002. Min Act: -0.1700
Data Index: 5110652 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6002. Min Act: -0.1700
Data Index: 2744055 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6315. Min Act: -0.1700
Data Index: 2527566 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.6002. Min Act: -0.1700
Data Index: 8466974 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.5690. Min Act: -0.1700
Data Index: 1010311 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.5377. Min Act: -0.1700
Data Index: 1966248 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.5377. Min Act: -0.1700
Data Index: 928655 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.4752. Min Act: -0.1700
Data Index: 1338986 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.5065. Min Act: -0.1700
Data Index: 6562760 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.5065. Min Act: -0.1700
Data Index: 8340775 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.4752. Min Act: -0.1700
Data Index: 30911 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.4752. Min Act: -0.1700
Data Index: 3342360 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7877. Min Range: -5.7877
Max Act: 5.4440. Min Act: -0.1700
Data Index: 1350684 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19