Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.9660. Min Act: -0.1700
Data Index: 6726596 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.8723. Min Act: -0.1700
Data Index: 4211948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.7785. Min Act: -0.1700
Data Index: 1775706 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.7785. Min Act: -0.1700
Data Index: 3510825 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1350457 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.6848. Min Act: -0.1700
Data Index: 3542408 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.6535. Min Act: -0.1700
Data Index: 2777384 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.6535. Min Act: -0.1700
Data Index: 5648408 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.6223. Min Act: -0.1700
Data Index: 3446882 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.6223. Min Act: -0.1700
Data Index: 8152276 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.5910. Min Act: -0.1700
Data Index: 3926001 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.5598. Min Act: -0.1700
Data Index: 6760414 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4973. Min Act: -0.1700
Data Index: 2234083 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4973. Min Act: -0.1700
Data Index: 6120554 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4973. Min Act: -0.1700
Data Index: 5165703 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4973. Min Act: -0.1700
Data Index: 8749564 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4348. Min Act: -0.1700
Data Index: 8505665 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4348. Min Act: -0.1700
Data Index: 5740952 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.4348. Min Act: -0.1700
Data Index: 4202976 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9660. Min Range: -5.9660
Max Act: 5.3723. Min Act: -0.1700
Data Index: 6647845 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19