Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0071. Min Range: -5.0071
Max Act: 5.0071. Min Act: -0.1700
Data Index: 1556931 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9133. Min Act: -0.1700
Data Index: 6507699 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8196. Min Act: -0.1700
Data Index: 96359 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6946. Min Act: -0.1700
Data Index: 8160341 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6946. Min Act: -0.1700
Data Index: 6480234 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6321. Min Act: -0.1700
Data Index: 4056093 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6321. Min Act: -0.1700
Data Index: 1284538 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5696. Min Act: -0.1700
Data Index: 2109732 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.6008. Min Act: -0.1700
Data Index: 8401209 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5696. Min Act: -0.1700
Data Index: 1052744 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5696. Min Act: -0.1700
Data Index: 952948 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5383. Min Act: -0.1700
Data Index: 4186661 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5383. Min Act: -0.1700
Data Index: 62311 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5071. Min Act: -0.1700
Data Index: 1018511 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.5071. Min Act: -0.1700
Data Index: 430860 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.4446. Min Act: -0.1700
Data Index: 2335461 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.4758. Min Act: -0.1700
Data Index: 2259948 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.4758. Min Act: -0.1700
Data Index: 1831431 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.4758. Min Act: -0.1700
Data Index: 2389436 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.4758. Min Act: -0.1700
Data Index: 885172 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19