Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.6611. Min Act: -0.1700
Data Index: 7697547 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.6298. Min Act: -0.1700
Data Index: 5208340 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.6298. Min Act: -0.1700
Data Index: 1005928 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.6298. Min Act: -0.1700
Data Index: 4504554 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5986. Min Act: -0.1700
Data Index: 4055541 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5673. Min Act: -0.1700
Data Index: 2734470 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5048. Min Act: -0.1700
Data Index: 4715361 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5361. Min Act: -0.1700
Data Index: 7845987 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5361. Min Act: -0.1700
Data Index: 5367897 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5048. Min Act: -0.1700
Data Index: 180561 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.5048. Min Act: -0.1700
Data Index: 2509398 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4736. Min Act: -0.1700
Data Index: 5200814 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4736. Min Act: -0.1700
Data Index: 7195240 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4736. Min Act: -0.1700
Data Index: 7903652 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4423. Min Act: -0.1700
Data Index: 5375717 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4111. Min Act: -0.1700
Data Index: 4877862 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4111. Min Act: -0.1700
Data Index: 7950127 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.4111. Min Act: -0.1700
Data Index: 3752598 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.3486. Min Act: -0.1700
Data Index: 7681096 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6611. Min Range: -4.6611
Max Act: 4.3486. Min Act: -0.1700
Data Index: 6107464 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19