Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1281. Min Range: -5.1281
Max Act: 5.1281. Min Act: -0.1700
Data Index: 7425142 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1281. Min Range: -5.1281
Max Act: 5.0968. Min Act: -0.1700
Data Index: 8706537 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1281. Min Range: -5.1281
Max Act: 5.0343. Min Act: -0.1700
Data Index: 2039868 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.9093. Min Act: -0.1700
Data Index: 8565548 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.9093. Min Act: -0.1700
Data Index: 2829305 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.9093. Min Act: -0.1700
Data Index: 2064670 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8781. Min Act: -0.1700
Data Index: 7473272 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8468. Min Act: -0.1700
Data Index: 8678605 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8156. Min Act: -0.1700
Data Index: 1836225 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8468. Min Act: -0.1700
Data Index: 7868598 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8156. Min Act: -0.1700
Data Index: 4862 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 7064852 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 6323441 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 8510674 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 83126 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 3154988 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 3866290 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7843. Min Act: -0.1700
Data Index: 684575 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8156. Min Act: -0.1700
Data Index: 606721 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7218. Min Act: -0.1700
Data Index: 2141843 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19