Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.2508. Min Act: -0.1700
Data Index: 7292038 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.2196. Min Act: -0.1700
Data Index: 7224914 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.1571. Min Act: -0.1700
Data Index: 5609300 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0946. Min Act: -0.1700
Data Index: 4911280 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0946. Min Act: -0.1700
Data Index: 4035056 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0633. Min Act: -0.1700
Data Index: 1627047 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0633. Min Act: -0.1700
Data Index: 3053452 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0321. Min Act: -0.1700
Data Index: 729849 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0321. Min Act: -0.1700
Data Index: 467844 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2508. Min Range: -6.2508
Max Act: 6.0321. Min Act: -0.1700
Data Index: 4493110 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.9696. Min Act: -0.1700
Data Index: 7292039 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.9696. Min Act: -0.1700
Data Index: 8194233 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.9696. Min Act: -0.1700
Data Index: 1294855 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.9071. Min Act: -0.1700
Data Index: 3256699 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.8446. Min Act: -0.1700
Data Index: 8464644 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.8446. Min Act: -0.1700
Data Index: 5295336 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.8446. Min Act: -0.1700
Data Index: 5255313 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.8446. Min Act: -0.1700
Data Index: 6419846 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.7821. Min Act: -0.1700
Data Index: 4227771 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2508. Min Range: -6.2508
Max Act: 5.7821. Min Act: -0.1700
Data Index: 4305028 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19