Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.8920. Min Act: -0.1700
Data Index: 7775666 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.8295. Min Act: -0.1700
Data Index: 4213519 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7982. Min Act: -0.1700
Data Index: 5772673 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7670. Min Act: -0.1700
Data Index: 6821258 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7670. Min Act: -0.1700
Data Index: 629430 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7670. Min Act: -0.1700
Data Index: 5653757 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4895829 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7045. Min Act: -0.1700
Data Index: 6184477 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7045. Min Act: -0.1700
Data Index: 899828 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7045. Min Act: -0.1700
Data Index: 5586570 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6732. Min Act: -0.1700
Data Index: 1417365 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6732. Min Act: -0.1700
Data Index: 2657575 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6420. Min Act: -0.1700
Data Index: 3836330 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.7045. Min Act: -0.1700
Data Index: 7517397 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6107. Min Act: -0.1700
Data Index: 3514101 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6420. Min Act: -0.1700
Data Index: 457442 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6420. Min Act: -0.1700
Data Index: 2259698 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6732. Min Act: -0.1700
Data Index: 1824772 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6420. Min Act: -0.1700
Data Index: 249452 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8920. Min Range: -4.8920
Max Act: 4.6420. Min Act: -0.1700
Data Index: 588290 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19