Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.8231. Min Act: -0.1700
Data Index: 6681995 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.7919. Min Act: -0.1700
Data Index: 6185096 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.7919. Min Act: -0.1700
Data Index: 1260853 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.7137. Min Act: -0.1700
Data Index: 6714956 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6824. Min Act: -0.1700
Data Index: 7983843 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6980. Min Act: -0.1700
Data Index: 7894415 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.7137. Min Act: -0.1700
Data Index: 3198628 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6667. Min Act: -0.1700
Data Index: 7180197 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6667. Min Act: -0.1700
Data Index: 4839731 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6824. Min Act: -0.1700
Data Index: 6870317 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6198. Min Act: -0.1700
Data Index: 6633636 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6511. Min Act: -0.1700
Data Index: 6693863 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6511. Min Act: -0.1700
Data Index: 2905862 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6354. Min Act: -0.1700
Data Index: 5881674 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6354. Min Act: -0.1700
Data Index: 7610553 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6041. Min Act: -0.1700
Data Index: 6481551 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6041. Min Act: -0.1700
Data Index: 1830614 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6041. Min Act: -0.1700
Data Index: 1024703 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.5885. Min Act: -0.1700
Data Index: 4374646 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8231. Min Range: -3.8231
Max Act: 3.6041. Min Act: -0.1700
Data Index: 8716795 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19