Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1299. Min Range: -6.1299
Max Act: 6.1299. Min Act: -0.1700
Data Index: 7209164 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1299. Min Range: -6.1299
Max Act: 6.0049. Min Act: -0.1700
Data Index: 6262683 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.9111. Min Act: -0.1700
Data Index: 4279189 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.8486. Min Act: -0.1700
Data Index: 2218384 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.7861. Min Act: -0.1700
Data Index: 6917465 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.7549. Min Act: -0.1700
Data Index: 4760073 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6611. Min Act: -0.1700
Data Index: 4506755 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6924. Min Act: -0.1700
Data Index: 5549450 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6924. Min Act: -0.1700
Data Index: 3028795 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6611. Min Act: -0.1700
Data Index: 4060666 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 670606 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 696473 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 3968652 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6611. Min Act: -0.1700
Data Index: 4707851 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 5583489 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.5986. Min Act: -0.1700
Data Index: 8083433 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.6299. Min Act: -0.1700
Data Index: 2401533 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.5986. Min Act: -0.1700
Data Index: 8032656 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.5674. Min Act: -0.1700
Data Index: 6571912 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1299. Min Range: -6.1299
Max Act: 5.5674. Min Act: -0.1700
Data Index: 3107096 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19