Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6469. Min Act: -0.1700
Data Index: 333690 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6157. Min Act: -0.1700
Data Index: 6784793 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.5532. Min Act: -0.1700
Data Index: 1851009 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4907. Min Act: -0.1700
Data Index: 5158699 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4282. Min Act: -0.1700
Data Index: 485086 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4282. Min Act: -0.1700
Data Index: 1725018 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4282. Min Act: -0.1700
Data Index: 1237132 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4282. Min Act: -0.1700
Data Index: 1226703 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3657. Min Act: -0.1700
Data Index: 1195208 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3344. Min Act: -0.1700
Data Index: 1786716 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3344. Min Act: -0.1700
Data Index: 7928321 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3032. Min Act: -0.1700
Data Index: 2051427 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2719. Min Act: -0.1700
Data Index: 8077989 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2407. Min Act: -0.1700
Data Index: 6103842 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6561803 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2407. Min Act: -0.1700
Data Index: 4730839 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6547017 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2094. Min Act: -0.1700
Data Index: 4501022 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2094. Min Act: -0.1700
Data Index: 7747765 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2094. Min Act: -0.1700
Data Index: 3496928 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19