Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.2660. Min Act: -0.1700
Data Index: 4556413 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.2660. Min Act: -0.1700
Data Index: 6637308 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.1723. Min Act: -0.1700
Data Index: 6794254 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.1723. Min Act: -0.1700
Data Index: 533271 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.1723. Min Act: -0.1700
Data Index: 8233724 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.1410. Min Act: -0.1700
Data Index: 7009595 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.1098. Min Act: -0.1700
Data Index: 7267421 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0473. Min Act: -0.1700
Data Index: 2741948 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0785. Min Act: -0.1700
Data Index: 1583654 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0785. Min Act: -0.1700
Data Index: 6185163 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.1098. Min Act: -0.1700
Data Index: 7528078 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0473. Min Act: -0.1700
Data Index: 7021160 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0160. Min Act: -0.1700
Data Index: 3463394 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0473. Min Act: -0.1700
Data Index: 8385271 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0160. Min Act: -0.1700
Data Index: 4187500 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0160. Min Act: -0.1700
Data Index: 2746286 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0160. Min Act: -0.1700
Data Index: 461429 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0160. Min Act: -0.1700
Data Index: 4696720 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2660. Min Range: -8.2660
Max Act: 7.9848. Min Act: -0.1700
Data Index: 1555957 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2660. Min Range: -8.2660
Max Act: 8.0160. Min Act: -0.1700
Data Index: 7026464 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19